Tootfinder

This https://arxiv.org/abs/2307.08424 has been replaced.
link: https://scholar.google.com/scholar?q=a

Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Model
Model inversion attacks (MIAs) aim to recover private data from inaccessible training sets of deep learning models, posing a privacy threat. MIAs primarily focus on the white-box scenario where attackers have full access to the model's structure and parameters. However, practical applications are usually in black-box scenarios or label-only scenarios, i.e., the attackers can only obtain the output confidence vectors or labels by accessing the model. Therefore, the attack models in existing MIAs…

Model Category Structure on Simplicial Algebras via Dold-Kan Correspondence
Hossein Faridian
https://arxiv.org/abs/2405.01752 https://

Model Category Structure on Simplicial Algebras via Dold-Kan Correspondence
This expository article sets forth a self-contained and purely algebraic proof of a deep result of Quillen stating that the category of simplicial commutative algebras over a commutative ring is a model category. This is accomplished by starting from the model structure on the category of connective chain complexes, transferring it to the category of simplicial modules via Dold-Kan Correspondence, and further transferring it to the category of simplicial commutative algebras through Quillen-Kan…

G4-Attention: Deep Learning Model with Attention for predicting DNA G-Quadruplexes
Shrimon Mukherjee, Pulakesh Pramanik, Partha Basuchowdhuri, Santanu Bhattacharya
https://arxiv.org/abs/2403.02765

G4-Attention: Deep Learning Model with Attention for predicting DNA G-Quadruplexes
G-Quadruplexes are the four-stranded non-canonical nucleic acid secondary structures, formed by the stacking arrangement of the guanine tetramers. They are involved in a wide range of biological roles because of their exceptionally unique and distinct structural characteristics. After the completion of the human genome sequencing project, a lot of bioinformatic algorithms were introduced to predict the active G4s regions \textit{in vitro} based on the canonical G4 sequence elements, G-\textit{r…

This https://arxiv.org/abs/2403.05771 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Providing Safety Assurances for Systems with Unknown Dynamics
As autonomous systems become more complex and integral in our society, the need to accurately model and safely control these systems has increased significantly. In the past decade, there has been tremendous success in using deep learning techniques to model and control systems that are difficult to model using first principles. However, providing safety assurances for such systems remains difficult, partially due to the uncertainty in the learned model. In this work, we aim to provide safety a…

Do You Trust Your Model? Emerging Malware Threats in the Deep Learning Ecosystem
Dorjan Hitaj, Giulio Pagnotta, Fabio De Gaspari, Sediola Ruko, Briland Hitaj, Luigi V. Mancini, Fernando Perez-Cruz
https://arxiv.org/abs/2403.03593

Do You Trust Your Model? Emerging Malware Threats in the Deep Learning Ecosystem
Training high-quality deep learning models is a challenging task due to computational and technical requirements. A growing number of individuals, institutions, and companies increasingly rely on pre-trained, third-party models made available in public repositories. These models are often used directly or integrated in product pipelines with no particular precautions, since they are effectively just data in tensor form and considered safe. In this paper, we raise awareness of a new machine lear…

All-in-One Deep Learning Framework for MR Image Reconstruction
Geunu Jeong, Hyeonsoo Kim, Joonyoung Yang, Kyungeun Jang, Jeewook Kim
https://arxiv.org/abs/2405.03684

All-in-One Deep Learning Framework for MR Image Reconstruction
We introduce a novel, all-in-one deep learning framework for MR image reconstruction, enabling a single model to enhance image quality across multiple aspects of k-space sampling and to be effective across a wide range of clinical and technical scenarios. This DICOM-based algorithm serves as the core of SwiftMR (AIRS Medical, Seoul, Korea), which is FDA-cleared, CE-certified, and commercially available. We first detail the comprehensive development process of the model, including data collectio…

This https://arxiv.org/abs/2403.11894 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

From Explainable to Interpretable Deep Learning for Natural Language Processing in Healthcare: How Far from Reality?
Deep learning (DL) has substantially enhanced natural language processing (NLP) in healthcare research. However, the increasing complexity of DL-based NLP necessitates transparent model interpretability, or at least explainability, for reliable decision-making. This work presents a thorough scoping review of explainable and interpretable DL in healthcare NLP. The term "eXplainable and Interpretable Artificial Intelligence" (XIAI) is introduced to distinguish XAI from IAI. Different models are f…

CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspections
Zhen Yao, Jiawei Xu, Shuhang Hou, Mooi Choo Chuah
https://arxiv.org/abs/2403.03063

CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspections
Routine visual inspections of concrete structures are imperative for upholding the safety and integrity of critical infrastructure. Such visual inspections sometimes happen under low-light conditions, e.g., checking for bridge health. Crack segmentation under such conditions is challenging due to the poor contrast between cracks and their surroundings. However, most deep learning methods are designed for well-illuminated crack images and hence their performance drops dramatically in low-light s…

A Federated Deep Learning Approach for Privacy-Preserving Real-Time Transient Stability Predictions in Power Systems
Maeshal Hijazi, Payman Dehghanian
https://arxiv.org/abs/2403.03126

A Federated Deep Learning Approach for Privacy-Preserving Real-Time Transient Stability Predictions in Power Systems
Maintaining the privacy of power system data is essential for protecting sensitive information and ensuring the operation security of critical infrastructure. Therefore, the adoption of centralized deep learning (DL) transient stability assessment (TSA) frameworks can introduce risks to electric utilities. This is because these frameworks make utility data susceptible to cyber threats and communication issues when transmitting data to a central server for training a single TSA model. Additional…

Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design
Jian Meng, Yuan Liao, Anupreetham Anupreetham, Ahmed Hasssan, Shixing Yu, Han-sok Suh, Xiaofeng Hu, Jae-sun Seo
https://arxiv.org/abs/2405.01775

Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design
The development of model compression is continuously motivated by the evolution of various neural network accelerators with ASIC or FPGA. On the algorithm side, the ultimate goal of quantization or pruning is accelerating the expensive DNN computations on low-power hardware. However, such a "design-and-deploy" workflow faces under-explored challenges in the current hardware-algorithm co-design community. First, although the state-of-the-art quantization algorithm can achieve low precision with …

FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models
Younghan Lee, Yungi Cho, Woorim Han, Ho Bae, Yunheung Paek
https://arxiv.org/abs/2403.02846

FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models
Federated Learning (FL) thrives in training a global model with numerous clients by only sharing the parameters of their local models trained with their private training datasets. Therefore, without revealing the private dataset, the clients can obtain a deep learning (DL) model with high performance. However, recent research proposed poisoning attacks that cause a catastrophic loss in the accuracy of the global model when adversaries, posed as benign clients, are present in a group of clients.…

TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation
Honghao Li, Yiwen Zhang, Yi Zhang, Lei Sang, Yun Yang
https://arxiv.org/abs/2405.03167

TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation
Effective feature interaction modeling is critical for enhancing the accuracy of click-through rate (CTR) prediction in industrial recommender systems. Most of the current deep CTR models resort to building complex network architectures to better capture intricate feature interactions or user behaviors. However, we identify two limitations in these models: (1) the samples given to the model are undifferentiated, which may lead the model to learn a larger number of easy samples in a single-minde…

DeepBioisostere: Discovering Bioisosteres with Deep Learning for a Fine Control of Multiple Molecular Properties
Hyeongwoo Kim, Seokhyun Moon, Wonho Zhung, Jaechang Lim, Woo Youn Kim
https://arxiv.org/abs/2403.02706

DeepBioisostere: Discovering Bioisosteres with Deep Learning for a Fine Control of Multiple Molecular Properties
Optimizing molecules to improve their properties is a fundamental challenge in drug design. For a fine-tuning of molecular properties without losing bio-activity validated in advance, the concept of bioisosterism has emerged. Many in silico methods have been proposed for discovering bioisosteres, but they require expert knowledge for their applications or are restricted to known databases. Here, we introduce DeepBioisostere, a deep generative model to design suitable bioisosteric replacements. …

A genome-scale deep learning model to predict gene expression changes of genetic perturbations from multiplex biological networks
Lingmin Zhan, Yuanyuan Zhang, Yingdong Wang, Aoyi Wang, Caiping Cheng, Jinzhong Zhao, Wuxia Zhang, Peng Lia, Jianxin Chen
https://arxiv.org/abs/2403.02724

A genome-scale deep learning model to predict gene expression changes of genetic perturbations from multiplex biological networks
Systematic characterization of biological effects to genetic perturbation is essential to the application of molecular biology and biomedicine. However, the experimental exhaustion of genetic perturbations on the genome-wide scale is challenging. Here, we show that TranscriptionNet, a deep learning model that integrates multiple biological networks to systematically predict transcriptional profiles to three types of genetic perturbations based on transcriptional profiles induced by genetic pert…

This https://arxiv.org/abs/2402.03383 has been replaced.
link: https://scholar.google.com/scholar?q=a

A Collaborative Model-driven Network for MRI Reconstruction
Deep learning (DL)-based methods offer a promising solution to reduce the prolonged scanning time in magnetic resonance imaging (MRI). While model-driven DL methods have demonstrated convincing results by incorporating prior knowledge into deep networks, further exploration is needed to optimize the integration of diverse priors.. Existing model-driven networks typically utilize linearly stacked unrolled cascades to mimic iterative solution steps in optimization algorithms. However, this approa…

From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings
Firuz Juraev, Mohammed Abuhamad, Eric Chan-Tin, George K. Thiruvathukal, Tamer Abuhmed
https://arxiv.org/abs/2405.01963

From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings
Deep Learning (DL) is rapidly maturing to the point that it can be used in safety- and security-crucial applications. However, adversarial samples, which are undetectable to the human eye, pose a serious threat that can cause the model to misbehave and compromise the performance of such applications. Addressing the robustness of DL models has become crucial to understanding and defending against adversarial attacks. In this study, we perform comprehensive experiments to examine the effect of ad…

Protein binding affinity prediction under multiple substitutions applying eGNNs on Residue and Atomic graphs combined with Language model information: eGRAL
Arturo Fiorellini-Bernardis, Sebastien Boyer, Christoph Brunken, Bakary Diallo, Karim Beguir, Nicolas Lopez-Carranza, Oliver Bent
https://arxiv.org/abs/2405.02374

Protein binding affinity prediction under multiple substitutions applying eGNNs on Residue and Atomic graphs combined with Language model information: eGRAL
Protein-protein interactions (PPIs) play a crucial role in numerous biological processes. Developing methods that predict binding affinity changes under substitution mutations is fundamental for modelling and re-engineering biological systems. Deep learning is increasingly recognized as a powerful tool capable of bridging the gap between in-silico predictions and in-vitro observations. With this contribution, we propose eGRAL, a novel SE(3) equivariant graph neural network (eGNN) architecture d…

A neuroergonomics model to evaluating nuclear power plants operators' performance under heat stress driven by ECG time-frequency spectrums and fNIRS prefrontal cortex network: a CNN-GAT fusion model
Yan Zhang, Ming Jia, Meng Li, JianYu Wang, XiangMin Hu, ZhiHui Xu, Tao Chen
https://arxiv.org/abs/2404.02439

A neuroergonomics model to evaluating nuclear power plants operators' performance under heat stress driven by ECG time-frequency spectrums and fNIRS prefrontal cortex network: a CNN-GAT fusion model
Operators experience complicated physiological and psychological states when exposed to extreme heat stress, which can impair cognitive function and decrease performance significantly, ultimately leading to severe secondary disasters. Therefore, there is an urgent need for a feasible technique to identify their abnormal states to enhance the reliability of human-cybernetics systems. With the advancement of deep learning in physiological modeling, a model for evaluating operators' performance dr…

This https://arxiv.org/abs/2207.02546 has been replaced.
link: https://scholar.google.com/scholar?q=a

Adaptive deep learning for nonlinear time series models
In this paper, we develop a general theory for adaptive nonparametric estimation of the mean function of a non-stationary and nonlinear time series model using deep neural networks (DNNs). We first consider two types of DNN estimators, non-penalized and sparse-penalized DNN estimators, and establish their generalization error bounds for general non-stationary time series. We then derive minimax lower bounds for estimating mean functions belonging to a wide class of nonlinear autoregressive (AR)…

A Federated Deep Learning Approach for Privacy-Preserving Real-Time Transient Stability Predictions in Power Systems
Maeshal Hijazi, Payman Dehghanian
https://arxiv.org/abs/2403.03126

A Federated Deep Learning Approach for Privacy-Preserving Real-Time Transient Stability Predictions in Power Systems
Maintaining the privacy of power system data is essential for protecting sensitive information and ensuring the operation security of critical infrastructure. Therefore, the adoption of centralized deep learning (DL) transient stability assessment (TSA) frameworks can introduce risks to electric utilities. This is because these frameworks make utility data susceptible to cyber threats and communication issues when transmitting data to a central server for training a single TSA model. Additional…

Mem-elements based Neuromorphic Hardware for Neural Network Application
Ankur Singh
https://arxiv.org/abs/2403.03002 https://arxiv.or…

Mem-elements based Neuromorphic Hardware for Neural Network Application
The thesis investigates the utilization of memristive and memcapacitive crossbar arrays in low-power machine learning accelerators, offering a comprehensive co-design framework for deep neural networks (DNN). The model, implemented through a hybrid Python and PyTorch approach, accounts for various non-idealities, achieving exceptional training accuracies of 90.02% and 91.03% for the CIFAR-10 dataset with memristive and memcapacitive crossbar arrays on an 8-layer VGG network. Additionally, the t…

DLAP: A Deep Learning Augmented Large Language Model Prompting Framework for Software Vulnerability Detection
Yanjing Yang, Xin Zhou, Runfeng Mao, Jinwei Xu, Lanxin Yang, Yu Zhangm, Haifeng Shen, He Zhang
https://arxiv.org/abs/2405.01202

DLAP: A Deep Learning Augmented Large Language Model Prompting Framework for Software Vulnerability Detection
Software vulnerability detection is generally supported by automated static analysis tools, which have recently been reinforced by deep learning (DL) models. However, despite the superior performance of DL-based approaches over rule-based ones in research, applying DL approaches to software vulnerability detection in practice remains a challenge due to the complex structure of source code, the black-box nature of DL, and the domain knowledge required to understand and validate the black-box res…

DEEP-IoT: Downlink-Enhanced Efficient-Power Internet of Things
Yulin Shao
https://arxiv.org/abs/2403.00321 https://arxiv.org/pdf/2403…

DEEP-IoT: Downlink-Enhanced Efficient-Power Internet of Things
At the heart of the Internet of Things (IoT) -- a domain witnessing explosive growth -- the imperative for energy efficiency and the extension of device lifespans has never been more pressing. This paper presents DEEP-IoT, a revolutionary communication paradigm poised to redefine how IoT devices communicate. Through a pioneering "listen more, transmit less" strategy, DEEP-IoT challenges and transforms the traditional transmitter (IoT devices)-centric communication model to one where the receive…

MR-Transformer: Vision Transformer for Total Knee Replacement Prediction Using Magnetic Resonance Imaging
Chaojie Zhang, Shengjia Chen, Ozkan Cigdem, Haresh Rengaraj Rajamohan, Kyunghyun Cho, Richard Kijowski, Cem M. Deniz
https://arxiv.org/abs/2405.02784

MR-Transformer: Vision Transformer for Total Knee Replacement Prediction Using Magnetic Resonance Imaging
A transformer-based deep learning model, MR-Transformer, was developed for total knee replacement (TKR) prediction using magnetic resonance imaging (MRI). The model incorporates the ImageNet pre-training and captures three-dimensional (3D) spatial correlation from the MR images. The performance of the proposed model was compared to existing state-of-the-art deep learning models for knee injury diagnosis using MRI. Knee MR scans of four different tissue contrasts from the Osteoarthritis Initiati…

This https://arxiv.org/abs/2404.02282 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Smooth Deep Saliency
In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling, with the purpose of explaining how a deep learning model detects tumors in scanned histological tissue samples. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden layers. We test our approach on different models trained for image classification on ImageNet1K, and models trained for tumor detection on Camelyon16 and…

This https://arxiv.org/abs/2308.10131 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_eco…

Agree to Disagree: Measuring Hidden Dissents in FOMC Meetings
Based on a record of dissents on FOMC votes and transcripts of the meetings from 1976 to 2017, we develop a deep learning model based on self-attention mechanism to create a measure of disagreement for members in each meeting. While dissents are rare, we find that members often have reservations with the policy decision, and the level of disagreement is mostly driven by current or predicted macroeconomic data. Using our model to evaluate speeches made by members between meetings, we find that t…

Diffraction and Scattering Aware Radio Map and Environment Reconstruction using Geometry Model-Assisted Deep Learning
Wangqian Chen, Junting Chen
https://arxiv.org/abs/2403.00229 …

Diffraction and Scattering Aware Radio Map and Environment Reconstruction using Geometry Model-Assisted Deep Learning
Machine learning (ML) facilitates rapid channel modeling for 5G and beyond wireless communication systems. Many existing ML techniques utilize a city map to construct the radio map; however, an updated city map may not always be available. This paper proposes to employ the received signal strength (RSS) data to jointly construct the radio map and the virtual environment by exploiting the geometry structure of the environment. In contrast to many existing ML approaches that lack of an environmen…

Deep Learning of ab initio Hessians for Transition State Optimization
Eric C. -Y. Yuan, Anup Kumar, Xingyi Guan, Eric D. Hermes, Andrew S. Rosen, Judit Z\'ador, Teresa Head-Gordon, Samuel M. Blau
https://arxiv.org/abs/2405.02247

Deep Learning of ab initio Hessians for Transition State Optimization
Identifying transition states -- saddle points on the potential energy surface connecting reactant and product minima -- is central to predicting kinetic barriers and understanding chemical reaction mechanisms. In this work, we train an equivariant neural network potential, NewtonNet, on an ab initio dataset of thousands of organic reactions from which we derive the analytical Hessians from the fully differentiable machine learning (ML) model. By reducing the computational cost by several order…

Explainable Risk Classification in Financial Reports
Xue Wen Tan, Stanley Kok
https://arxiv.org/abs/2405.01881 https://arxiv.org/pdf/…

Explainable Risk Classification in Financial Reports
Every publicly traded company in the US is required to file an annual 10-K financial report, which contains a wealth of information about the company. In this paper, we propose an explainable deep-learning model, called FinBERT-XRC, that takes a 10-K report as input, and automatically assesses the post-event return volatility risk of its associated company. In contrast to previous systems, our proposed model simultaneously offers explanations of its classification decision at three different le…

This https://arxiv.org/abs/2401.10557 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Newton's method and its hybrid with machine learning for Navier-Stokes Darcy Models discretized by mixed element methods
This paper focuses on discussing Newton's method and its hybrid with machine learning for the steady state Navier-Stokes Darcy model discretized by mixed element methods. First, a Newton iterative method is introduced for solving the relative discretized problem. It is proved technically that this method converges quadratically with the convergence rate independent of the finite element mesh size, under certain standard conditions. Later on, a deep learning algorithm is proposed for solving thi…

This https://arxiv.org/abs/2302.05797 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Global Convergence Rate of Deep Equilibrium Models with General Activations
In a recent paper, Ling et al. investigated the over-parametrized Deep Equilibrium Model (DEQ) with ReLU activation. They proved that the gradient descent converges to a globally optimal solution for the quadratic loss function at a linear convergence rate. This paper shows that this fact still holds for DEQs with any generally bounded activation with bounded first and second derivatives. Since the new activation function is generally non-homogeneous, bounding the least eigenvalue of the Gram m…

This https://arxiv.org/abs/2404.02282 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Smooth Deep Saliency
In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling, with the purpose of explaining how a deep learning model detects tumors in scanned histological tissue samples. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden layers. We test our approach on different models trained for image classification on ImageNet1K, and models trained for tumor detection on Camelyon16 and…

These absolute fartwaffles can’t conceive of anyone having moral objections to bad things, because they don’t think people who aren’t like themselves have any value.
No, there must be some other reason.
Peer pressure. Not enough sex on campus (yes, really, Google it). Soros paying them. Antisemitism. Brainwashing.
Anything but the simplest explanation: good people demanding that bad people stop what they’re doing.

This https://arxiv.org/abs/2305.12844 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

An Optimized Ensemble Deep Learning Model For Brain Tumor Classification
Brain tumors present a grave risk to human life, demanding precise and timely diagnosis for effective treatment. Inaccurate identification of brain tumors can significantly diminish life expectancy, underscoring the critical need for precise diagnostic methods. Manual identification of brain tumors within vast Magnetic Resonance Imaging (MRI) image datasets is arduous and time-consuming. Thus, the development of a reliable deep learning (DL) model is essential to enhance diagnostic accuracy and…

This https://arxiv.org/abs/2401.06846 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Simulation-based inference of deep fields: galaxy population model and redshift distributions
Accurate redshift calibration is required to obtain unbiased cosmological information from large-scale galaxy surveys. In a forward modelling approach, the redshift distribution n(z) of a galaxy sample is measured using a parametric galaxy population model constrained by observations. We use a model that captures the redshift evolution of the galaxy luminosity functions, colours, and morphology, for red and blue samples. We constrain this model via simulation-based inference, using factorized A…

Steganographic Passport: An Owner and User Verifiable Credential for Deep Model IP Protection Without Retraining
Qi Cui, Ruohan Meng, Chaohui Xu, Chip-Hong Chang
https://arxiv.org/abs/2404.02889

Steganographic Passport: An Owner and User Verifiable Credential for Deep Model IP Protection Without Retraining
Ensuring the legal usage of deep models is crucial to promoting trustable, accountable, and responsible artificial intelligence innovation. Current passport-based methods that obfuscate model functionality for license-to-use and ownership verifications suffer from capacity and quality constraints, as they require retraining the owner model for new users. They are also vulnerable to advanced Expanded Residual Block ambiguity attacks. We propose Steganographic Passport, which uses an invertible s…

DeepVARMA: A Hybrid Deep Learning and VARMA Model for Chemical Industry Index Forecasting
Xiang Li, Hu Yang
https://arxiv.org/abs/2404.17615 https://

DeepVARMA: A Hybrid Deep Learning and VARMA Model for Chemical Industry Index Forecasting
Since the chemical industry index is one of the important indicators to measure the development of the chemical industry, forecasting it is critical for understanding the economic situation and trends of the industry. Taking the multivariable nonstationary series-synthetic material index as the main research object, this paper proposes a new prediction model: DeepVARMA, and its variants Deep-VARMA-re and DeepVARMA-en, which combine LSTM and VARMAX models. The new model firstly uses the deep lea…

"By 1973, the first volume of the defining work of our craft, “The Art of Computer Programming” had been available in bookstores since 1968, and its first chapter literally consisted of a 100-something page long introduction to various mathematical concepts. Induction, logarithms, series, matrices, elementary number theory, permutations and factorials, Fibonacci numbers, are some of the subjects exposed in those beautifully typeset pages."

In Praise Of Mathematics
How much math knowledge does a programmer need to know to fulfill their job? How deep should the mathematical knowledge of full-stack engineers, computer security experts, or large language model engineers be? The spectrum of possible answers to these questions is too large to be useful. Perhaps the eternal answer "it depends" is enough?

This https://arxiv.org/abs/2306.04205 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Exploring Quantum Synchronization with a Composite Two-Qubit Oscillator
Synchronization has recently been explored deep in the quantum regime with elementary few-level quantum oscillators such as qudits and weakly pumped quantum Van der Pol oscillators. To engineer more complex quantum synchronizing systems, it is practically relevant to study composite oscillators built up from basic quantum units that are commonly available and offer high controllability. Here, we consider a minimal model for a composite oscillator consisting of two interacting qubits coupled to …

The Impact of Frequency Bands on Acoustic Anomaly Detection of Machines using Deep Learning Based Model
Tin Nguyen, Lam Pham, Phat Lam, Dat Ngo, Hieu Tang, Alexander Schindler
https://arxiv.org/abs/2403.00379

The Impact of Frequency Bands on Acoustic Anomaly Detection of Machines using Deep Learning Based Model
In this paper, we propose a deep learning based model for Acoustic Anomaly Detection of Machines, the task for detecting abnormal machines by analysing the machine sound. By conducting extensive experiments, we indicate that multiple techniques of pseudo audios, audio segment, data augmentation, Mahalanobis distance, and narrow frequency bands, which mainly focus on feature engineering, are effective to enhance the system performance. Among the evaluating techniques, the narrow frequency bands …

Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment
Aditya Chakravarty
https://arxiv.org/abs/2405.01004

Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment
Recent transformer-based ASR models have achieved word-error rates (WER) below 4%, surpassing human annotator accuracy, yet they demand extensive server resources, contributing to significant carbon footprints. The traditional server-based architecture of ASR also presents privacy concerns, alongside reliability and latency issues due to network dependencies. In contrast, on-device (edge) ASR enhances privacy, boosts performance, and promotes sustainability by effectively balancing energy use a…

This https://arxiv.org/abs/2309.03493 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

SAM3D: Segment Anything Model in Volumetric Medical Images
Image segmentation remains a pivotal component in medical image analysis, aiding in the extraction of critical information for precise diagnostic practices. With the advent of deep learning, automated image segmentation methods have risen to prominence, showcasing exceptional proficiency in processing medical imagery. Motivated by the Segment Anything Model (SAM)-a foundational model renowned for its remarkable precision and robust generalization capabilities in segmenting 2D natural images-we …

This https://arxiv.org/abs/2308.10131 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_eco…

Agree to Disagree: Measuring Hidden Dissents in FOMC Meetings
Based on a record of dissents on FOMC votes and transcripts of the meetings from 1976 to 2017, we develop a deep learning model based on self-attention mechanism to create a measure of disagreement for members in each meeting. While dissents are rare, we find that members often have reservations with the policy decision, and the level of disagreement is mostly driven by current or predicted macroeconomic data. Using our model to evaluate speeches made by members between meetings, we find that t…

Improved model-free bounds for multi-asset options using option-implied information and deep learning
Evangelia Dragazi, Shuaiqiang Liu, Antonis Papapantoleon
https://arxiv.org/abs/2404.02343

Improved model-free bounds for multi-asset options using option-implied information and deep learning
We consider the computation of model-free bounds for multi-asset options in a setting that combines dependence uncertainty with additional information on the dependence structure. More specifically, we consider the setting where the marginal distributions are known and partial information, in the form of known prices for multi-asset options, is also available in the market. We provide a fundamental theorem of asset pricing in this setting, as well as a superhedging duality that allows to transf…

Powering In-Database Dynamic Model Slicing for Structured Data Analytics
Lingze Zeng, Naili Xing, Shaofeng Cai, Gang Chen, Beng Chin Ooi, Jian Pei, Yuncheng Wu
https://arxiv.org/abs/2405.00568

Powering In-Database Dynamic Model Slicing for Structured Data Analytics
Relational database management systems (RDBMS) are widely used for the storage and retrieval of structured data. To derive insights beyond statistical aggregation, we typically have to extract specific subdatasets from the database using conventional database operations, and then apply deep neural networks (DNN) training and inference on these respective subdatasets in a separate machine learning system. The process can be prohibitively expensive, especially when there are a combinatorial numbe…

Ensemble Deep Learning for enhanced seismic data reconstruction
Mohammad Mahdi Abedi, David Pardo, Tariq Alkhalifah
https://arxiv.org/abs/2404.02632 https:…

Ensemble Deep Learning for enhanced seismic data reconstruction
Seismic data often contain gaps due to various obstacles in the investigated area and recording instrument failures. Deep learning techniques offer promising solutions for reconstructing missing data parts by leveraging existing information. However, self-supervised methods frequently struggle with capturing under-represented features such as weaker events, crossing dips, and higher frequencies. To address these challenges, we propose a novel ensemble deep model along with a tailored self-super…

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
A N M Nafiz Abeer, Sanket Jantre, Nathan M Urban, Byung-Jun Yoon
https://arxiv.org/abs/2405.00202

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
Deep generative models have been accelerating the inverse design process in material and drug design. Unlike their counterpart property predictors in typical molecular design frameworks, generative molecular design models have seen fewer efforts on uncertainty quantification (UQ) due to computational challenges in Bayesian inference posed by their large number of parameters. In this work, we focus on the junction-tree variational autoencoder (JT-VAE), a popular model for generative molecular de…

Solar synthetic imaging: Introducing denoising diffusion probabilistic models on SDO/AIA data
Francesco P. Ramunno, S. Hackstein, V. Kinakh, M. Drozdova, G. Quetant, A. Csillaghy, S. Voloshynovskiy
https://arxiv.org/abs/2404.02552

Solar synthetic imaging: Introducing denoising diffusion probabilistic models on SDO/AIA data
Given the rarity of significant solar flares compared to smaller ones, training effective machine learning models for solar activity forecasting is challenging due to insufficient data. This study proposes using generative deep learning models, specifically a Denoising Diffusion Probabilistic Model (DDPM), to create synthetic images of solar phenomena, including flares of varying intensities. By employing a dataset from the AIA instrument aboard the SDO spacecraft, focusing on the 171 Å band t…

Collaborative Optimization of Wireless Communication and Computing Resource Allocation based on Multi-Agent Federated Weighting Deep Reinforcement Learning
Junjie Wu, Xuming Fang
https://arxiv.org/abs/2404.01638

Collaborative Optimization of Wireless Communication and Computing Resource Allocation based on Multi-Agent Federated Weighting Deep Reinforcement Learning
As artificial intelligence (AI)-enabled wireless communication systems continue their evolution, distributed learning has gained widespread attention for its ability to offer enhanced data privacy protection, improved resource utilization, and enhanced fault tolerance within wireless communication applications. Federated learning further enhances the ability of resource coordination and model generalization across nodes based on the above foundation, enabling the realization of an AI-driven com…

This https://arxiv.org/abs/2310.04621 has been replaced.
link: https://scholar.google.com/scholar?q=a

Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences
On-device machine learning (ML) promises to improve the privacy, responsiveness, and proliferation of new, intelligent user experiences by moving ML computation onto everyday personal devices. However, today's large ML models must be drastically compressed to run efficiently on-device, a hurtle that requires deep, yet currently niche expertise. To engage the broader human-centered ML community in on-device ML experiences, we present the results from an interview study with 30 experts at Apple t…

Model-based Deep Learning for Rate Split Multiple Access in Vehicular Communications
Hanwen Zhang, Mingzhe Chen, Alireza Vahid, Haijian Sun
https://arxiv.org/abs/2405.01515

Model-based Deep Learning for Rate Split Multiple Access in Vehicular Communications
Rate split multiple access (RSMA) has been proven as an effective communication scheme for 5G and beyond, especially in vehicular scenarios. However, RSMA requires complicated iterative algorithms for proper resource allocation, which cannot fulfill the stringent latency requirement in resource constrained vehicles. Although data driven approaches can alleviate this issue, they suffer from poor generalizability and scarce training data. In this paper, we propose a fractional programming (FP) ba…

Deep generative modelling of canonical ensemble with differentiable thermal properties
Shuo-Hui Li, Yao-Wen Zhang, Ding Pan
https://arxiv.org/abs/2404.18404

Deep generative modelling of canonical ensemble with differentiable thermal properties
We propose a variational modelling method with differentiable temperature for canonical ensembles. Using a deep generative model, the free energy is estimated and minimized simultaneously in a continuous temperature range. At optimal, this generative model is a Boltzmann distribution with temperature dependence. The training process requires no dataset, and works with arbitrary explicit density generative models. We applied our method to study the phase transitions (PT) in the Ising and XY mode…

This https://arxiv.org/abs/2401.10557 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Newton's method and its hybrid with machine learning for Navier-Stokes Darcy Models discretized by mixed element methods
This paper focuses on discussing Newton's method and its hybrid with machine learning for the steady state Navier-Stokes Darcy model discretized by mixed element methods. First, a Newton iterative method is introduced for solving the relative discretized problem. It is proved technically that this method converges quadratically with the convergence rate independent of the finite element mesh size, under certain standard conditions. Later on, a deep learning algorithm is proposed for solving thi…

Spatio-Temporal Graph Convolutional Network Combined Large Language Model: A Deep Learning Framework for Bike Demand Forecasting
Peisen Li, Yizhe Pang, Junyu Ren
https://arxiv.org/abs/2403.15733

Spatio-Temporal Graph Convolutional Network Combined Large Language Model: A Deep Learning Framework for Bike Demand Forecasting
This study presents a new deep learning framework, combining Spatio-Temporal Graph Convolutional Network (STGCN) with a Large Language Model (LLM), for bike demand forecasting. Addressing challenges in transforming discrete datasets and integrating unstructured language data, the framework leverages LLMs to extract insights from Points of Interest (POI) text data. The proposed STGCN-L model demonstrates competitive performance compared to existing models, showcasing its potential in predicting …

Optimizing Portfolio Management and Risk Assessment in Digital Assets Using Deep Learning for Predictive Analysis
Qishuo Cheng, Le Yang, Jiajian Zheng, Miao Tian, Duan Xin
https://arxiv.org/abs/2402.15994 https://arxiv.org/pdf/2402.15994
arXiv:2402.15994v1 Announce Type: new
Abstract: Portfolio management issues have been extensively studied in the field of artificial intelligence in recent years, but existing deep learning-based quantitative trading methods have some areas where they could be improved. First of all, the prediction mode of stocks is singular; often, only one trading expert is trained by a model, and the trading decision is solely based on the prediction results of the model. Secondly, the data source used by the model is relatively simple, and only considers the data of the stock itself, ignoring the impact of the whole market risk on the stock. In this paper, the DQN algorithm is introduced into asset management portfolios in a novel and straightforward way, and the performance greatly exceeds the benchmark, which fully proves the effectiveness of the DRL algorithm in portfolio management. This also inspires us to consider the complexity of financial problems, and the use of algorithms should be fully combined with the problems to adapt. Finally, in this paper, the strategy is implemented by selecting the assets and actions with the largest Q value. Since different assets are trained separately as environments, there may be a phenomenon of Q value drift among different assets (different assets have different Q value distribution areas), which may easily lead to incorrect asset selection. Consider adding constraints so that the Q values of different assets share a Q value distribution to improve results.

This https://arxiv.org/abs/2302.13056 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

SATBA: An Invisible Backdoor Attack Based On Spatial Attention
Backdoor attack has emerged as a novel and concerning threat to AI security. These attacks involve the training of Deep Neural Network (DNN) on datasets that contain hidden trigger patterns. Although the poisoned model behaves normally on benign samples, it exhibits abnormal behavior on samples containing the trigger pattern. However, most existing backdoor attacks suffer from two significant drawbacks: their trigger patterns are visible and easy to detect by backdoor defense or even human insp…

SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising
Guanyiman Fu, Fengchao Xiong, Jianfeng Lu, Jun Zhou, Yuntao Qian
https://arxiv.org/abs/2405.01726

SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising
Denoising hyperspectral images (HSIs) is a crucial preprocessing procedure due to the noise originating from intra-imaging mechanisms and environmental factors. Utilizing domain-specific knowledge of HSIs, such as spectral correlation, spatial self-similarity, and spatial-spectral correlation, is essential for deep learning-based denoising. Existing methods are often constrained by running time, space complexity, and computational complexity, employing strategies that explore these priors separ…

Behavior Imitation for Manipulator Control and Grasping with Deep Reinforcement Learning
Liu Qiyuan
https://arxiv.org/abs/2405.01284 https://

Behavior Imitation for Manipulator Control and Grasping with Deep Reinforcement Learning
The existing Motion Imitation models typically require expert data obtained through MoCap devices, but the vast amount of training data needed is difficult to acquire, necessitating substantial investments of financial resources, manpower, and time. This project combines 3D human pose estimation with reinforcement learning, proposing a novel model that simplifies Motion Imitation into a prediction problem of joint angle values in reinforcement learning. This significantly reduces the reliance o…

These absolute fartwaffles can’t conceive of anyone having moral objections to bad things, because they don’t think people who aren’t like themselves have any value.
No, there must be some other reason.
Peer pressure. Not enough sex on campus (yes, really, Google it). Soros paying them. Antisemitism. Brainwashing.
Anything but the simplest explanation: good people demanding that bad people stop what they’re doing.

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
A N M Nafiz Abeer, Sanket Jantre, Nathan M Urban, Byung-Jun Yoon
https://arxiv.org/abs/2405.00202

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
Deep generative models have been accelerating the inverse design process in material and drug design. Unlike their counterpart property predictors in typical molecular design frameworks, generative molecular design models have seen fewer efforts on uncertainty quantification (UQ) due to computational challenges in Bayesian inference posed by their large number of parameters. In this work, we focus on the junction-tree variational autoencoder (JT-VAE), a popular model for generative molecular de…

This https://arxiv.org/abs/2404.10727 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model
Understanding what makes high-dimensional data learnable is a fundamental question in machine learning. On the one hand, it is believed that the success of deep learning lies in its ability to build a hierarchy of representations that become increasingly more abstract with depth, going from simple features like edges to more complex concepts. On the other hand, learning to be insensitive to invariances of the task, such as smooth transformations for image datasets, has been argued to be importa…

This https://arxiv.org/abs/2310.04621 has been replaced.
link: https://scholar.google.com/scholar?q=a

Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences
On-device machine learning (ML) promises to improve the privacy, responsiveness, and proliferation of new, intelligent user experiences by moving ML computation onto everyday personal devices. However, today's large ML models must be drastically compressed to run efficiently on-device, a hurtle that requires deep, yet currently niche expertise. To engage the broader human-centered ML community in on-device ML experiences, we present the results from an interview study with 30 experts at Apple t…

Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment
Aditya Chakravarty
https://arxiv.org/abs/2405.01004

Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment
Recent transformer-based ASR models have achieved word-error rates (WER) below 4%, surpassing human annotator accuracy, yet they demand extensive server resources, contributing to significant carbon footprints. The traditional server-based architecture of ASR also presents privacy concerns, alongside reliability and latency issues due to network dependencies. In contrast, on-device (edge) ASR enhances privacy, boosts performance, and promotes sustainability by effectively balancing energy use a…

This https://arxiv.org/abs/2311.18377 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Transfer Learning across Different Chemical Domains: Virtual Screening of Organic Materials with Deep Learning Models Pretrained on Small Molecule and Chemical Reaction Data
Machine learning is becoming a preferred method for the virtual screening of organic materials due to its cost-effectiveness over traditional computationally demanding techniques. However, the scarcity of labeled data for organic materials poses a significant challenge for training advanced machine learning models. This study showcases the potential of utilizing databases of drug-like small molecules and chemical reactions to pretrain the BERT model, enhancing its performance in the virtual scr…

This https://arxiv.org/abs/2402.18929 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution
Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years. %Despite the substantial advancement% While most existing work assumes a simple and fixed degradation model (e.g., bicubic downsampling), the research of Blind SR seeks to improve model generalization ability with unknown degradation. Recently, Kong et al pioneer the investigation of a more suitable training strategy for Blind SR using Dropout. Although such method indeed brings substa…

This https://arxiv.org/abs/2312.15101 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Fix-Con: Automatic Fault Localization and Repair of Deep Learning Model Conversions between Frameworks
Converting deep learning models between frameworks is a common step to maximize model compatibility across devices and leverage optimization features that may be exclusively provided in one deep learning framework. However, this conversion process may be riddled with bugs, making the converted models either undeployable or problematic, considerably degrading their prediction correctness. In this paper we propose an automated approach for fault localization and repair, Fix-Con, during model co…

Ensemble Deep Learning for enhanced seismic data reconstruction
Mohammad Mahdi Abedi, David Pardo, Tariq Alkhalifah
https://arxiv.org/abs/2404.02632 https:…

Ensemble Deep Learning for enhanced seismic data reconstruction
Seismic data often contain gaps due to various obstacles in the investigated area and recording instrument failures. Deep learning techniques offer promising solutions for reconstructing missing data parts by leveraging existing information. However, self-supervised methods frequently struggle with capturing under-represented features such as weaker events, crossing dips, and higher frequencies. To address these challenges, we propose a novel ensemble deep model along with a tailored self-super…

Model Free Deep Deterministic Policy Gradient Controller for Setpoint Tracking of Non-minimum Phase Systems
Fatemeh Tavakkoli, Pouria Sarhadi, Benoit Clement, Wasif Naeem
https://arxiv.org/abs/2402.17703

Model Free Deep Deterministic Policy Gradient Controller for Setpoint Tracking of Non-minimum Phase Systems
Deep Reinforcement Learning (DRL) techniques have received significant attention in control and decision-making algorithms. Most applications involve complex decision-making systems, justified by the algorithms' computational power and cost. While model-based versions are emerging, model-free DRL approaches are intriguing for their independence from models, yet they remain relatively less explored in terms of performance, particularly in applied control. This study conducts a thorough performan…

This https://arxiv.org/abs/2405.01726 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising
Denoising hyperspectral images (HSIs) is a crucial preprocessing procedure due to the noise originating from intra-imaging mechanisms and environmental factors. Utilizing domain-specific knowledge of HSIs, such as spectral correlation, spatial self-similarity, and spatial-spectral correlation, is essential for deep learning-based denoising. Existing methods are often constrained by running time, space complexity, and computational complexity, employing strategies that explore these priors separ…

A thermodynamically consistent physics-informed deep learning material model for short fiber/polymer nanocomposites
Betim Bahtiri, Behrouz Arash, Sven Scheffler, Maximilian Jux, Raimund Rolfes
https://arxiv.org/abs/2403.18310

A thermodynamically consistent physics-informed deep learning material model for short fiber/polymer nanocomposites
This work proposes a physics-informed deep learning (PIDL)-based constitutive model for investigating the viscoelastic-viscoplastic behavior of short fiber-reinforced nanoparticle-filled epoxies under various ambient conditions. The deep-learning model is trained to enforce thermodynamic principles, leading to a thermodynamically consistent constitutive model. To accomplish this, a long short-term memory network is combined with a feed-forward neural network to predict internal variables requir…

This https://arxiv.org/abs/2304.06607 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

False Claims against Model Ownership Resolution
Deep neural network (DNN) models are valuable intellectual property of model owners, constituting a competitive advantage. Therefore, it is crucial to develop techniques to protect against model theft. Model ownership resolution (MOR) is a class of techniques that can deter model theft. A MOR scheme enables an accuser to assert an ownership claim for a suspect model by presenting evidence, such as a watermark or fingerprint, to show that the suspect model was stolen or derived from a source mod…

Predicting the Temperature Dependence of Surfactant CMCs Using Graph Neural Networks
Christoforos Brozos, Jan G. Rittig, Sandip Bhattacharya, Elie Akanny, Christina Kohlmann, Alexander Mitsos
https://arxiv.org/abs/2403.03767

Predicting the Temperature Dependence of Surfactant CMCs Using Graph Neural Networks
The critical micelle concentration (CMC) of surfactant molecules is an essential property for surfactant applications in industry. Recently, classical QSPR and Graph Neural Networks (GNNs), a deep learning technique, have been successfully applied to predict the CMC of surfactants at room temperature. However, these models have not yet considered the temperature dependency of the CMC, which is highly relevant for practical applications. We herein develop a GNN model for temperature-dependent CM…

This https://arxiv.org/abs/2402.19276 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Modular Blind Video Quality Assessment
Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services. Contemporary deep learning-based models primarily analyze the video content in its aggressively downsampled format, while being blind to the impact of actual spatial resolution and frame rate on video quality. In this paper, we propose a modular BVQA model, and a method of training it to improve its modularity. Spec…

NeuralSI: Neural Design of Semantic Interaction for Interactive Deep Learning
Yali Bian, Rebecca Faust, Chris North
https://arxiv.org/abs/2402.17178 https:…

NeuralSI: Neural Design of Semantic Interaction for Interactive Deep Learning
An increasing number of studies have utilized interactive deep learning as the analytic model of visual analytics systems for complex sensemaking tasks. In these systems, traditional interactive dimensionality reduction (DR) models are commonly utilized to build a bi-directional bridge between high-dimensional deep learning representations and low-dimensional visualizations. While these systems better capture analysts' intents in the context of human-in-the-loop interactive deep learning, tradi…

Practical Dataset Distillation Based on Deep Support Vectors
Hyunho Lee, Junhoo Lee, Nojun Kwak
https://arxiv.org/abs/2405.00348 https://

Practical Dataset Distillation Based on Deep Support Vectors
Conventional dataset distillation requires significant computational resources and assumes access to the entire dataset, an assumption impractical as it presumes all data resides on a central server. In this paper, we focus on dataset distillation in practical scenarios with access to only a fraction of the entire dataset. We introduce a novel distillation method that augments the conventional process by incorporating general model knowledge via the addition of Deep KKT (DKKT) loss. In practica…

This https://arxiv.org/abs/2310.01642 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Naming Practices of Pre-Trained Models in Hugging Face
As innovation in deep learning continues, many engineers seek to adopt Pre-Trained Models (PTMs) as components in computer systems. Researchers publish PTMs, which engineers adapt for quality or performance prior to deployment. PTM authors should choose appropriate names for their PTMs, which would facilitate model discovery and reuse. However, prior research has reported that model names are not always well chosen - and are sometimes erroneous. The naming for PTM packages has not been systemat…

This https://arxiv.org/abs/2306.06112 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

ModelObfuscator: Obfuscating Model Information to Protect Deployed ML-based Systems
More and more edge devices and mobile apps are leveraging deep learning (DL) capabilities. Deploying such models on devices -- referred to as on-device models -- rather than as remote cloud-hosted services, has gained popularity because it avoids transmitting user data off of the device and achieves high response time. However, on-device models can be easily attacked, as they can be accessed by unpacking corresponding apps and the model is fully exposed to attackers. Recent studies show that at…

Practical Dataset Distillation Based on Deep Support Vectors
Hyunho Lee, Junhoo Lee, Nojun Kwak
https://arxiv.org/abs/2405.00348 https://

Practical Dataset Distillation Based on Deep Support Vectors
Conventional dataset distillation requires significant computational resources and assumes access to the entire dataset, an assumption impractical as it presumes all data resides on a central server. In this paper, we focus on dataset distillation in practical scenarios with access to only a fraction of the entire dataset. We introduce a novel distillation method that augments the conventional process by incorporating general model knowledge via the addition of Deep KKT (DKKT) loss. In practica…

This https://arxiv.org/abs/2203.13856 has been replaced.
link: https://scholar.google.com/scholar?q=a

Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalization
Deep learning applications for assessing medical images are limited because the datasets are often small and imbalanced. The use of synthetic data has been proposed in the literature, but neither a robust comparison of the different methods nor generalizability has been reported. Our approach integrates a retinal image quality assessment model and StyleGAN2 architecture to enhance Age-related Macular Degeneration (AMD) detection capabilities and improve generalizability. This work compares ten …

GAD-Generative Learning for HD Map-Free Autonomous Driving
Weijian Sun, Yanbo Jia, Qi Zeng, Zihao Liu, Jiang Liao, Yue Li, Xianfeng Li, Bolin Zhao
https://arxiv.org/abs/2405.00515

GAD-Generative Learning for HD Map-Free Autonomous Driving
Deep-learning-based techniques have been widely adopted for autonomous driving software stacks for mass production in recent years, focusing primarily on perception modules, with some work extending this method to prediction modules. However, the downstream planning and control modules are still designed with hefty handcrafted rules, dominated by optimization-based methods such as quadratic programming or model predictive control. This results in a performance bottleneck for autonomous driving …

This https://arxiv.org/abs/2306.06112 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

ModelObfuscator: Obfuscating Model Information to Protect Deployed ML-based Systems
More and more edge devices and mobile apps are leveraging deep learning (DL) capabilities. Deploying such models on devices -- referred to as on-device models -- rather than as remote cloud-hosted services, has gained popularity because it avoids transmitting user data off of the device and achieves high response time. However, on-device models can be easily attacked, as they can be accessed by unpacking corresponding apps and the model is fully exposed to attackers. Recent studies show that at…

Unsupervised Binary Code Translation with Application to Code Similarity Detection and Vulnerability Discovery
Iftakhar Ahmad, Lannan Luo
https://arxiv.org/abs/2404.19025

Unsupervised Binary Code Translation with Application to Code Similarity Detection and Vulnerability Discovery
Binary code analysis has immense importance in the research domain of software security. Today, software is very often compiled for various Instruction Set Architectures (ISAs). As a result, cross-architecture binary code analysis has become an emerging problem. Recently, deep learning-based binary analysis has shown promising success. It is widely known that training a deep learning model requires a massive amount of data. However, for some low-resource ISAs, an adequate amount of data is hard…

Inline AI: Open-source Deep Learning Inference for Cardiac MR
Hui Xue, Rhodri H Davies, James Howard, Hunain Shiwani, Azaan Rehman, Iain Pierce, Henry Procter, Marianna Fontana, James C Moon, Eylem Levelt, Peter Kellman
https://arxiv.org/abs/2404.02384

Inline AI: Open-source Deep Learning Inference for Cardiac MR
Cardiac Magnetic Resonance (CMR) is established as a non-invasive imaging technique for evaluation of heart function, anatomy, and myocardial tissue characterization. Quantitative biomarkers are central for diagnosis and management of heart disease. Deep learning (DL) is playing an ever more important role in extracting these quantitative measures from CMR images. While many researchers have reported promising results in training and evaluating models, model deployment into the imaging workflow…

This https://arxiv.org/abs/2308.15808 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Learning the References of Online Model Predictive Control for Urban Self-Driving
In this work, we propose a novel learning-based model predictive control (MPC) framework for motion planning and control of urban self-driving. In this framework, instantaneous references and cost functions of online MPC are learned from raw sensor data without relying on any oracle or predicted states of traffic. Moreover, driving safety conditions are latently encoded via the introduction of a learnable instantaneous reference vector. In particular, we implement a deep reinforcement learning …

This https://arxiv.org/abs/2304.06607 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

False Claims against Model Ownership Resolution
Deep neural network (DNN) models are valuable intellectual property of model owners, constituting a competitive advantage. Therefore, it is crucial to develop techniques to protect against model theft. Model ownership resolution (MOR) is a class of techniques that can deter model theft. A MOR scheme enables an accuser to assert an ownership claim for a suspect model by presenting evidence, such as a watermark or fingerprint, to show that the suspect model was stolen or derived from a source mod…

Deep Learning for Traffic Flow Prediction using Cellular Automata-based Model and CNN-LSTM architecture
Zhaohui Yang, Kshitij Jerath
https://arxiv.org/abs/2403.18710

Deep Learning for Traffic Flow Prediction using Cellular Automata-based Model and CNN-LSTM architecture
Recent works have attempted to use deep learning to predict future states of traffic flow, but have met with mixed results. These approaches face two key challenges. First, training deep learning neural networks requires large amounts of training data which are not yet easily available for traffic flow systems. Second, even when data is available, the neural networks require access to historical data that covers most possible traffic flow dynamics to successfully predict future traffic states. …

Model-less Is the Best Model: Generating Pure Code Implementations to Replace On-Device DL Models
Mingyi Zhou, Xiang Gao, Pei Liu, John Grundy, Chunyang Chen, Xiao Chen, Li Li
https://arxiv.org/abs/2403.16479

Model-less Is the Best Model: Generating Pure Code Implementations to Replace On-Device DL Models
Recent studies show that deployed deep learning (DL) models such as those of Tensor Flow Lite (TFLite) can be easily extracted from real-world applications and devices by attackers to generate many kinds of attacks like adversarial attacks. Although securing deployed on-device DL models has gained increasing attention, no existing methods can fully prevent the aforementioned threats. Traditional software protection techniques have been widely explored, if on-device models can be implemented usi…

This https://arxiv.org/abs/2404.11766 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

End-to-End Mesh Optimization of a Hybrid Deep Learning Black-Box PDE Solver
Deep learning has been widely applied to solve partial differential equations (PDEs) in computational fluid dynamics. Recent research proposed a PDE correction framework that leverages deep learning to correct the solution obtained by a PDE solver on a coarse mesh. However, end-to-end training of such a PDE correction model over both solver-dependent parameters such as mesh parameters and neural network parameters requires the PDE solver to support automatic differentiation through the iterativ…

Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projects
Han Wang, Sijia Yu, Chunyang Chen, Burak Turhan, Xiaodong Zhu
https://arxiv.org/abs/2402.16546

Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projects
Deep Learning (DL) models have rapidly advanced, focusing on achieving high performance through testing model accuracy and robustness. However, it is unclear whether DL projects, as software systems, are tested thoroughly or functionally correct when there is a need to treat and test them like other software systems. Therefore, we empirically study the unit tests in open-source DL projects, analyzing 9,129 projects from GitHub. We find that: 1) unit tested DL projects have positive correlation …

MisGUIDE : Defense Against Data-Free Deep Learning Model Extraction
Mahendra Gurve, Sankar Behera, Satyadev Ahlawat, Yamuna Prasad
https://arxiv.org/abs/2403.18580

MisGUIDE : Defense Against Data-Free Deep Learning Model Extraction
The rise of Machine Learning as a Service (MLaaS) has led to the widespread deployment of machine learning models trained on diverse datasets. These models are employed for predictive services through APIs, raising concerns about the security and confidentiality of the models due to emerging vulnerabilities in prediction APIs. Of particular concern are model cloning attacks, where individuals with limited data and no knowledge of the training dataset manage to replicate a victim model's functio…

Nonlinear model reduction for operator learning
Hamidreza Eivazi, Stefan Wittek, Andreas Rausch
https://arxiv.org/abs/2403.18735 https://

Nonlinear model reduction for operator learning
Operator learning provides methods to approximate mappings between infinite-dimensional function spaces. Deep operator networks (DeepONets) are a notable architecture in this field. Recently, an extension of DeepONet based on model reduction and neural networks, proper orthogonal decomposition (POD)-DeepONet, has been able to outperform other architectures in terms of accuracy for several benchmark tests. We extend this idea towards nonlinear model order reduction by proposing an efficient fram…

Relaxometry Guided Quantitative Cardiac Magnetic Resonance Image Reconstruction
Yidong Zhao, Yi Zhang, Qian Tao
https://arxiv.org/abs/2403.00549 https://…

Relaxometry Guided Quantitative Cardiac Magnetic Resonance Image Reconstruction
Deep learning-based methods have achieved prestigious performance for magnetic resonance imaging (MRI) reconstruction, enabling fast imaging for many clinical applications. Previous methods employ convolutional networks to learn the image prior as the regularization term. In quantitative MRI, the physical model of nuclear magnetic resonance relaxometry is known, providing additional prior knowledge for image reconstruction. However, traditional reconstruction networks are limited to learning th…

Gradient-based Automatic Per-Weight Mixed Precision Quantization for Neural Networks On-Chip
Chang Sun, Thea K. {\AA}rrestad, Vladimir Loncar, Jennifer Ngadiuba, Maria Spiropulu
https://arxiv.org/abs/2405.00645

Gradient-based Automatic Per-Weight Mixed Precision Quantization for Neural Networks On-Chip
Model size and inference speed at deployment time, are major challenges in many deep learning applications. A promising strategy to overcome these challenges is quantization. However, a straightforward uniform quantization to very low precision can result in significant accuracy loss. Mixed-precision quantization, based on the idea that certain parts of the network can accommodate lower precision without compromising performance compared to other parts, offers a potential solution. In this work…

Proteus: Preserving Model Confidentiality during Graph Optimizations
Yubo Gao, Maryam Haghifam, Christina Giannoula, Renbo Tu, Gennady Pekhimenko, Nandita Vijaykumar
https://arxiv.org/abs/2404.12512

Proteus: Preserving Model Confidentiality during Graph Optimizations
Deep learning (DL) models have revolutionized numerous domains, yet optimizing them for computational efficiency remains a challenging endeavor. Development of new DL models typically involves two parties: the model developers and performance optimizers. The collaboration between the parties often necessitates the model developers exposing the model architecture and computational graph to the optimizers. However, this exposure is undesirable since the model architecture is an important intellec…

Gradient-based Automatic Per-Weight Mixed Precision Quantization for Neural Networks On-Chip
Chang Sun, Thea K. {\AA}rrestad, Vladimir Loncar, Jennifer Ngadiuba, Maria Spiropulu
https://arxiv.org/abs/2405.00645

Gradient-based Automatic Per-Weight Mixed Precision Quantization for Neural Networks On-Chip
Model size and inference speed at deployment time, are major challenges in many deep learning applications. A promising strategy to overcome these challenges is quantization. However, a straightforward uniform quantization to very low precision can result in significant accuracy loss. Mixed-precision quantization, based on the idea that certain parts of the network can accommodate lower precision without compromising performance compared to other parts, offers a potential solution. In this work…

A vascular synthetic model for improved aneurysm segmentation and detection via Deep Neural Networks
Rafic Nader, Florent Autrusseau, Vincent L'Allinec, Romain Bourcier
https://arxiv.org/abs/2403.18734

A vascular synthetic model for improved aneurysm segmentation and detection via Deep Neural Networks
We hereby present a full synthetic model, able to mimic the various constituents of the cerebral vascular tree: the cerebral arteries, the bifurcations and the intracranial aneurysms. By building this model, our goal was to provide a substantial dataset of brain arteries which could be used by a 3D Convolutional Neural Network (CNN) to either segment or detect/recognize various vascular diseases (such as artery dissection/thrombosis) or even some portions of the cerebral vasculature, such as th…

Enhancing Deep Learning Model Explainability in Brain Tumor Datasets using Post-Heuristic Approaches
Konstantinos Pasvantis, Eftychios Protopapadakis
https://arxiv.org/abs/2404.19568 https://arxiv.org/pdf/2404.19568
arXiv:2404.19568v1 Announce Type: new
Abstract: The application of deep learning models in medical diagnosis has showcased considerable efficacy in recent years. Nevertheless, a notable limitation involves the inherent lack of explainability during decision-making processes. This study addresses such a constraint, by enhancing the interpretability robustness. The primary focus is directed towards refining the explanations generated by the LIME Library and LIME image explainer. This is achieved throuhg post-processing mechanisms, based on scenario-specific rules. Multiple experiments have been conducted using publicly accessible datasets related to brain tumor detection. Our proposed post-heuristic approach demonstrates significant advancements, yielding more robust and concrete results, in the context of medical diagnosis.

TorchSurv: A Lightweight Package for Deep Survival Analysis
M\'elodie Monod, Peter Krusche, Qian Cao, Berkman Sahiner, Nicholas Petrick, David Ohlssen, Thibaud Coroller
https://arxiv.org/abs/2404.10761

TorchSurv: A Lightweight Package for Deep Survival Analysis
TorchSurv is a Python package that serves as a companion tool to perform deep survival modeling within the PyTorch environment. Unlike existing libraries that impose specific parametric forms, TorchSurv enables the use of custom PyTorch-based deep survival models. With its lightweight design, minimal input requirements, full PyTorch backend, and freedom from restrictive survival model parameterizations, TorchSurv facilitates efficient deep survival model implementation and is particularly benef…

LpQcM: Adaptable Lesion-Quantification-Consistent Modulation for Deep Learning Low-Count PET Image Denoising
Menghua Xia, Huidong Xie, Qiong Liu, Bo Zhou, Hanzhong Wang, Biao Li, Axel Rominger, Kuangyu Shi, Georges EI Fakhri, Chi Liu
https://arxiv.org/abs/2404.17994 https://arxiv.org/pdf/2404.17994
arXiv:2404.17994v1 Announce Type: new
Abstract: Deep learning-based positron emission tomography (PET) image denoising offers the potential to reduce radiation exposure and scanning time by transforming low-count images into high-count equivalents. However, existing methods typically blur crucial details, leading to inaccurate lesion quantification. This paper proposes a lesion-perceived and quantification-consistent modulation (LpQcM) strategy for enhanced PET image denoising, via employing downstream lesion quantification analysis as auxiliary tools. The LpQcM is a plug-and-play design adaptable to a wide range of model architectures, modulating the sampling and optimization procedures of model training without adding any computational burden to the inference phase. Specifically, the LpQcM consists of two components, the lesion-perceived modulation (LpM) and the multiscale quantification-consistent modulation (QcM). The LpM enhances lesion contrast and visibility by allocating higher sampling weights and stricter loss criteria to lesion-present samples determined by an auxiliary segmentation network than lesion-absent ones. The QcM further emphasizes accuracy of quantification for both the mean and maximum standardized uptake value (SUVmean and SUVmax) across multiscale sub-regions throughout the entire image, thereby enhancing the overall image quality. Experiments conducted on large PET datasets from multiple centers and vendors, and varying noise levels demonstrated the LpQcM efficacy across various denoising frameworks. Compared to frameworks without LpQcM, the integration of LpQcM reduces the lesion SUVmean bias by 2.92% on average and increases the peak signal-to-noise ratio (PSNR) by 0.34 on average, for denoising images of extremely low-count levels below 10%.

Optimizing Universal Lesion Segmentation: State Space Model-Guided Hierarchical Networks with Feature Importance Adjustment
Kazi Shahriar Sanjid, Md. Tanzim Hossain, Md. Shakib Shahariar Junayed, M. Monir Uddin
https://arxiv.org/abs/2404.17235

Optimizing Universal Lesion Segmentation: State Space Model-Guided Hierarchical Networks with Feature Importance Adjustment
Deep learning has revolutionized medical imaging by providing innovative solutions to complex healthcare challenges. Traditional models often struggle to dynamically adjust feature importance, resulting in suboptimal representation, particularly in tasks like semantic segmentation crucial for accurate structure delineation. Moreover, their static nature incurs high computational costs. To tackle these issues, we introduce Mamba-Ahnet, a novel integration of State Space Model (SSM) and Advanced …