Tootfinder

Measurement of atmospheric #neutrino oscillation parameters using #ConvolutionalNeuralNetworks with 9.3 years of data in #IceCube DeepCore: https://arxiv.org/abs/2405.02163 -> Measurement of atmospheric neutrino oscillation parameters using convolutional neural networks with high precision: https://icecube.wisc.edu/news/research/2024/05/measurement-of-atmospheric-neutrino-oscillation-parameters-using-convolutional-neural-networks-with-high-precision/

celegansneural: C. elegans neurons (1986)
A network representing the neural connections of the Caenorhabditis elegans nematode.
This network has 297 nodes and 2359 edges.
Tags: Biological, Connectome, Weighted
https://networks.skewed.de/net/celegansneural…

Using Neural Networks to Model Hysteretic Kinematics in Tendon-Actuated Continuum Robots
Yuan Wang, Max McCandless, Abdulhamit Donder, Giovanni Pittiglio, Behnam Moradkhani, Yash Chitalia, Pierre E. Dupont
https://arxiv.org/abs/2404.07168

Using Neural Networks to Model Hysteretic Kinematics in Tendon-Actuated Continuum Robots
The ability to accurately model mechanical hysteretic behavior in tendon-actuated continuum robots using deep learning approaches is a growing area of interest. In this paper, we investigate the hysteretic response of two types of tendon-actuated continuum robots and, ultimately, compare three types of neural network modeling approaches with both forward and inverse kinematic mappings: feedforward neural network (FNN), FNN with a history input buffer, and long short-term memory (LSTM) network. …

Node Centrality Approximation For Large Networks Based On Inductive Graph Neural Networks
Yiwei Zou, Ting Li, Zong-fu Luo
https://arxiv.org/abs/2403.04977 …

Node Centrality Approximation For Large Networks Based On Inductive Graph Neural Networks
Closeness Centrality (CC) and Betweenness Centrality (BC) are crucial metrics in network analysis, providing essential reference for discerning the significance of nodes within complex networks. These measures find wide applications in critical tasks, such as community detection and network dismantling. However, their practical implementation on extensive networks remains computationally demanding due to their high time complexity. To mitigate these computational challenges, numerous approximat…

This https://arxiv.org/abs/2401.04628 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Multi-Neuron Representations of Hierarchical Concepts in Spiking Neural Networks
We describe how hierarchical concepts can be represented in three types of layered neural networks. The aim is to support recognition of the concepts when partial information about the concepts is presented, and also when some of the neurons in the network might fail. Our failure model involves initial random failures. The three types of networks are: feed-forward networks with high connectivity, feed-forward networks with low connectivity, and layered networks with low connectivity and with bo…

This https://arxiv.org/abs/2301.06136 has been replaced.
link: https://scholar.google.com/scholar?q=a

Quantitative Verification with Neural Networks
We present a data-driven approach to the quantitative verification of probabilistic programs and stochastic dynamical models. Our approach leverages neural networks to compute tight and sound bounds for the probability that a stochastic process hits a target condition within finite time. This problem subsumes a variety of quantitative verification questions, from the reachability and safety analysis of discrete-time stochastic dynamical models, to the study of assertion-violation and terminatio…

Neural networks can be FLOP-efficient integrators of 1D oscillatory integrands
Anshuman Sinha, Spencer H. Bryngelson
https://arxiv.org/abs/2404.05938 https…

Neural networks can be FLOP-efficient integrators of 1D oscillatory integrands
We demonstrate that neural networks can be FLOP-efficient integrators of one-dimensional oscillatory integrands. We train a feed-forward neural network to compute integrals of highly oscillatory 1D functions. The training set is a parametric combination of functions with varying characters and oscillatory behavior degrees. Numerical examples show that these networks are FLOP-efficient for sufficiently oscillatory integrands with an average FLOP gain of 1000 FLOPs. The network calculates oscilla…

Fuel-optimal powered descent guidance for lunar pinpoint landing using neural networks
Kun Wang, Zheng Chen, Jun Li
https://arxiv.org/abs/2404.06722 https:…

Fuel-optimal powered descent guidance for lunar pinpoint landing using neural networks
This paper presents a Neural Networks (NNs) based approach for designing the Fuel-Optimal Powered Descent Guidance (FOPDG) for lunar pinpoint landing. According to Pontryagin's Minimum Principle, the optimality conditions are first derived. To generate the dataset of optimal trajectories for training NNs, we formulate a parameterized system, which allows for generating each optimal trajectory by a simple propagation without using any optimization method. Then, a dataset containing the optimal s…

This https://arxiv.org/abs/2311.07620 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAR_…

EPIM: Efficient Processing-In-Memory Accelerators based on Epitome
The utilization of large-scale neural networks on Processing-In-Memory (PIM) accelerators encounters challenges due to constrained on-chip memory capacity. To tackle this issue, current works explore model compression algorithms to reduce the size of Convolutional Neural Networks (CNNs). Most of these algorithms either aim to represent neural operators with reduced-size parameters (e.g., quantization) or search for the best combinations of neural operators (e.g., neural architecture search). De…

Onboard Processing of Hyperspectral Imagery: Deep Learning Advancements, Methodologies, Challenges, and Emerging Trends
Nafiseh Ghasemi, Jon Alvarez Justo, Marco Celesti, Laurent Despoisse, Jens Nieke
https://arxiv.org/abs/2404.06526

Onboard Processing of Hyperspectral Imagery: Deep Learning Advancements, Methodologies, Challenges, and Emerging Trends
Recent advancements in deep learning techniques have spurred considerable interest in their application to hyperspectral imagery processing. This paper provides a comprehensive review of the latest developments in this field, focusing on methodologies, challenges, and emerging trends. Deep learning architectures such as Convolutional Neural Networks (CNNs), Autoencoders, Deep Belief Networks (DBNs), Generative Adversarial Networks (GANs), and Recurrent Neural Networks (RNNs) are examined for th…

Deploying Graph Neural Networks in Wireless Networks: A Link Stability Viewpoint
Jun Li, Weiwei Zhang, Kang Wei, Guangji Chen, Long Shi, Wen Chen
https://arxiv.org/abs/2405.05802 …

Deploying Graph Neural Networks in Wireless Networks: A Link Stability Viewpoint
As an emerging artificial intelligence technology, graph neural networks (GNNs) have exhibited promising performance across a wide range of graph-related applications. However, information exchanges among neighbor nodes in GNN pose new challenges in the resource-constrained scenario, especially in wireless systems. In practical wireless systems, the communication links among nodes are usually unreliable due to wireless fading and receiver noise, consequently resulting in performance degradation…

This https://arxiv.org/abs/2402.14515 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Spectral invariance and maximality properties of the frequency spectrum of quantum neural networks
Quantum Neural Networks (QNNs) are a popular approach in Quantum Machine Learning due to their close connection to Variational Quantum Circuits, making them a promising candidate for practical applications on Noisy Intermediate-Scale Quantum (NISQ) devices. A QNN can be expressed as a finite Fourier series, where the set of frequencies is called the frequency spectrum. We analyse this frequency spectrum and prove, for a large class of models, various maximality results. Furthermore, we prove th…

Identification of Settling Velocity with Physics Informed Neural Networks For Sediment Laden Flows
Micka\"el Delcey, Yoann Cheny, Jean-Baptiste Keck, Adrien Gans, S\'ebastien Kiesgen De Richter
https://arxiv.org/abs/2404.06802

Identification of Settling Velocity with Physics Informed Neural Networks For Sediment Laden Flows
Physics-Informed Neural Networks (PINNs) have shown great potential in the context of fluid dynamics simulations, particularly in reconstructing flow fields and identifying key parameters. In this study, we explore the application of PINNs to recover the dimensionless settling velocity for sedimentation flow. The flow involves sediment-laden fresh water overlying salt water, which is described by Navier-Stokes equations coupled with sediment concentration and salinity transport equations. Two c…

This https://arxiv.org/abs/2401.12321 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csGT_…

The outcomes of generative AI are exactly the Nash equilibria of a non-potential game
In this article we show that the asymptotic outcomes of both shallow and deep neural networks such as those used in BloombergGPT to generate economic time series are exactly the Nash equilibria of a non-potential game. We then design and analyze deep neural network algorithms that converge to these equilibria. The methodology is extended to federated deep neural networks between clusters of regional servers and on-device clients. Finally, the variational inequalities behind large language model…

Model-Free Local Recalibration of Neural Networks
R. TorresUniversity of Bras\'ilia, D. J. NottNational University of Singapore, S. A. SissonUniversity of New South Wales, Sydney, T. RodriguesUniversity of Bras\'ilia, J. G. ReisUniversity of Bras\'ilia, G. S. RodriguesUniversity of Bras\'ilia
https://arxiv.org/ab…

Model-Free Local Recalibration of Neural Networks
Artificial neural networks (ANNs) are highly flexible predictive models. However, reliably quantifying uncertainty for their predictions is a continuing challenge. There has been much recent work on "recalibration" of predictive distributions for ANNs, so that forecast probabilities for events of interest are consistent with certain frequency evaluations of them. Uncalibrated probabilistic forecasts are of limited use for many important decision-making tasks. To address this issue, we propose a…

Lyapunov-Based Deep Residual Neural Network (ResNet) Adaptive Control
Omkar Sudhir Patil, Duc M. Le, Emily J. Griffis, Warren E. Dixon
https://arxiv.org/abs/2404.07385

Lyapunov-Based Deep Residual Neural Network (ResNet) Adaptive Control
Deep Neural Network (DNN)-based controllers have emerged as a tool to compensate for unstructured uncertainties in nonlinear dynamical systems. A recent breakthrough in the adaptive control literature provides a Lyapunov-based approach to derive weight adaptation laws for each layer of a fully-connected feedforward DNN-based adaptive controller. However, deriving weight adaptation laws from a Lyapunov-based analysis remains an open problem for deep residual neural networks (ResNets). This paper…

Jet Discrimination with Quantum Complete Graph Neural Network
Yi-An Chen, Kai-Feng Chen
https://arxiv.org/abs/2403.04990 https://arxi…

Jet Discrimination with Quantum Complete Graph Neural Network
Machine learning, particularly deep neural networks, has been widely utilized in high energy physics and has shown remarkable results in various applications. Moreover, the concept of machine learning has been extended to quantum computers, giving rise to a new research area known as quantum machine learning. In this paper, we propose a novel variational quantum circuit model, Quantum Complete Graph Neural Network (QCGNN), designed for learning complete graphs. We argue that QCGNN has a polynom…

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural

Solving Parametric PDEs with Radial Basis Functions and Deep Neural Networks
Guanhang Lei, Zhen Lei, Lei Shi, Chenyu Zeng
https://arxiv.org/abs/2404.06834 …

Solving Parametric PDEs with Radial Basis Functions and Deep Neural Networks
We propose the POD-DNN, a novel algorithm leveraging deep neural networks (DNNs) along with radial basis functions (RBFs) in the context of the proper orthogonal decomposition (POD) reduced basis method (RBM), aimed at approximating the parametric mapping of parametric partial differential equations on irregular domains. The POD-DNN algorithm capitalizes on the low-dimensional characteristics of the solution manifold for parametric equations, alongside the inherent offline-online computational …

Message Passing Variational Autoregressive Network for Solving Intractable Ising Models
Qunlong Ma, Zhi Ma, Jinlong Xu, Hairui Zhang, Ming Gao
https://arxiv.org/abs/2404.06225

Message Passing Variational Autoregressive Network for Solving Intractable Ising Models
Many deep neural networks have been used to solve Ising models, including autoregressive neural networks, convolutional neural networks, recurrent neural networks, and graph neural networks. Learning a probability distribution of energy configuration or finding the ground states of a disordered, fully connected Ising model is essential for statistical mechanics and NP-hard problems. Despite tremendous efforts, a neural network architecture with the ability to high-accurately solve these fully c…

This https://arxiv.org/abs/2310.12557 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text
Spatial reasoning in text plays a crucial role in various real-world applications. Existing approaches for spatial reasoning typically infer spatial relations from pure text, which overlooks the gap between natural language and symbolic structures. Graph neural networks (GNNs) have showcased exceptional proficiency in inducing and aggregating symbolic structures. However, classical GNNs face challenges in handling multi-hop spatial reasoning due to the over-smoothing issue, i.e., the performanc…

sVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks
Qu Yang, Qianhui Liu, Nan Li, Meng Ge, Zeyang Song, Haizhou Li
https://arxiv.org/abs/2403.05772

sVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks
Speech applications are expected to be low-power and robust under noisy conditions. An effective Voice Activity Detection (VAD) front-end lowers the computational need. Spiking Neural Networks (SNNs) are known to be biologically plausible and power-efficient. However, SNN-based VADs have yet to achieve noise robustness and often require large models for high performance. This paper introduces a novel SNN-based VAD model, referred to as sVAD, which features an auditory encoder with an SNN-based …

Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks
Marco De Nadai, Francesco Fabbri, Paul Gigioli, Alice Wang, Ang Li, Fabrizio Silvestri, Laura Kim, Shawn Lin, Vladan Radosavljevic, Sandeep Ghael, David Nyhan, Hugues Bouchard, Mounia Lalmas-Roelleke, Andreas Damianou
https://arxiv.org/abs/2403.05185…

Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks
In the ever-evolving digital audio landscape, Spotify, well-known for its music and talk content, has recently introduced audiobooks to its vast user base. While promising, this move presents significant challenges for personalized recommendations. Unlike music and podcasts, audiobooks, initially available for a fee, cannot be easily skimmed before purchase, posing higher stakes for the relevance of recommendations. Furthermore, introducing a new content type into an existing platform confronts…

1-bit Quantized On-chip Hybrid Diffraction Neural Network Enabled by Authentic All-optical Fully-connected Architecture
Yu Shao, Haiqi Gao, Yipeng Chen, Yujie liu, Junren Wen, Haidong He, Yuchuan Shao, Yueguang Zhang, Weidong Shen, Chenying Yang
https://arxiv.org/abs/2404.07443

1-bit Quantized On-chip Hybrid Diffraction Neural Network Enabled by Authentic All-optical Fully-connected Architecture
Optical Diffraction Neural Networks (DNNs), a subset of Optical Neural Networks (ONNs), show promise in mirroring the prowess of electronic networks. This study introduces the Hybrid Diffraction Neural Network (HDNN), a novel architecture that incorporates matrix multiplication into DNNs, synergizing the benefits of conventional ONNs with those of DNNs to surmount the modulation limitations inherent in optical diffraction neural networks. Utilizing a singular phase modulation layer and an ampli…

Link Stealing Attacks Against Inductive Graph Neural Networks
Yixin Wu, Xinlei He, Pascal Berrang, Mathias Humbert, Michael Backes, Neil Zhenqiang Gong, Yang Zhang
https://arxiv.org/abs/2405.05784

Link Stealing Attacks Against Inductive Graph Neural Networks
A graph neural network (GNN) is a type of neural network that is specifically designed to process graph-structured data. Typically, GNNs can be implemented in two settings, including the transductive setting and the inductive setting. In the transductive setting, the trained model can only predict the labels of nodes that were observed at the training time. In the inductive setting, the trained model can be generalized to new nodes/graphs. Due to its flexibility, the inductive setting is the mo…

Learning Traveling Solitary Waves Using Separable Gaussian Neural Networks
Siyuan Xing, Efstathios G. Charalampidis
https://arxiv.org/abs/2403.04883 https:…

Learning Traveling Solitary Waves Using Separable Gaussian Neural Networks
In this paper, we apply a machine-learning approach to learn traveling solitary waves across various families of partial differential equations (PDEs). Our approach integrates a novel interpretable neural network (NN) architecture, called Separable Gaussian Neural Networks (SGNN) into the framework of Physics-Informed Neural Networks (PINNs). Unlike the traditional PINNs that treat spatial and temporal data as independent inputs, the present method leverages wave characteristics to transform da…

This https://arxiv.org/abs/2405.02220 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Designed Dithering Sign Activation for Binary Neural Networks
Binary Neural Networks emerged as a cost-effective and energy-efficient solution for computer vision tasks by binarizing either network weights or activations. However, common binary activations, such as the Sign activation function, abruptly binarize the values with a single threshold, losing fine-grained details in the feature outputs. This work proposes an activation that applies multiple thresholds following dithering principles, shifting the Sign activation function for each pixel accordin…

Cellular automata, many-valued logic, and deep neural networks
Yani Zhang, Helmut B\"olcskei
https://arxiv.org/abs/2404.05259 https://

Cellular automata, many-valued logic, and deep neural networks
We develop a theory characterizing the fundamental capability of deep neural networks to learn, from evolution traces, the logical rules governing the behavior of cellular automata (CA). This is accomplished by first establishing a novel connection between CA and Lukasiewicz propositional logic. While binary CA have been known for decades to essentially perform operations in Boolean logic, no such relationship exists for general CA. We demonstrate that many-valued (MV) logic, specifically Lukas…

Simultaneous linear connectivity of neural networks modulo permutation
Ekansh Sharma, Devin Kwok, Tom Denton, Daniel M. Roy, David Rolnick, Gintare Karolina Dziugaite
https://arxiv.org/abs/2404.06498

Simultaneous linear connectivity of neural networks modulo permutation
Neural networks typically exhibit permutation symmetries which contribute to the non-convexity of the networks' loss landscapes, since linearly interpolating between two permuted versions of a trained network tends to encounter a high loss barrier. Recent work has argued that permutation symmetries are the only sources of non-convexity, meaning there are essentially no such barriers between trained networks if they are permuted appropriately. In this work, we refine these arguments into three d…

Channel Estimation for Stacked Intelligent Metasurface-Assisted Wireless Networks
Xianghao Yao, Jiancheng An, Lu Gan, Marco Di Renzo, Chau Yuen
https://arxiv.org/abs/2403.05870

Channel Estimation for Stacked Intelligent Metasurface-Assisted Wireless Networks
Emerging technologies, such as holographic multiple-input multiple-output (HMIMO) and stacked intelligent metasurface (SIM), are driving the development of wireless communication systems. Specifically, the SIM is physically constructed by stacking multiple layers of metasurfaces and has an architecture similar to an artificial neural network (ANN), which can flexibly manipulate the electromagnetic waves that propagate through it at the speed of light. This architecture enables the SIM to achiev…

Fast System Technology Co-Optimization Framework for Emerging Technology Based on Graph Neural Networks
Tianliang Ma, Guangxi Fan, Xuguang Sun, Zhihui Deng, Kainlu Low, Leilai Shao
https://arxiv.org/abs/2404.06939

Fast System Technology Co-Optimization Framework for Emerging Technology Based on Graph Neural Networks
This paper proposes a fast system technology co-optimization (STCO) framework that optimizes power, performance, and area (PPA) for next-generation IC design, addressing the challenges and opportunities presented by novel materials and device architectures. We focus on accelerating the technology level of STCO using AI techniques, by employing graph neural network (GNN)-based approaches for both TCAD simulation and cell library characterization, which are interconnected through a unified compac…

A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes
Alessandro Benfenati, Alessio Marta
https://arxiv.org/abs/2404.06104

A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes
Neural networks are playing a crucial role in everyday life, with the most modern generative models able to achieve impressive results. Nonetheless, their functioning is still not very clear, and several strategies have been adopted to study how and why these model reach their outputs. A common approach is to consider the data in an Euclidean settings: recent years has witnessed instead a shift from this paradigm, moving thus to more general framework, namely Riemannian Geometry. Two recent wor…

SiGNN: A Spike-induced Graph Neural Network for Dynamic Graph Representation Learning
Dong Chen, Shuai Zheng, Muhao Xu, Zhenfeng Zhu, Yao Zhao
https://arxiv.org/abs/2404.07941

SiGNN: A Spike-induced Graph Neural Network for Dynamic Graph Representation Learning
In the domain of dynamic graph representation learning (DGRL), the efficient and comprehensive capture of temporal evolution within real-world networks is crucial. Spiking Neural Networks (SNNs), known as their temporal dynamics and low-power characteristic, offer an efficient solution for temporal processing in DGRL task. However, owing to the spike-based information encoding mechanism of SNNs, existing DGRL methods employed SNNs face limitations in their representational capacity. Given this …

Hybridized Convolutional Neural Networks and Long Short-Term Memory for Improved Alzheimer's Disease Diagnosis from MRI Scans
Maleka Khatun, Md Manowarul Islam, Habibur Rahman Rifat, Md. Shamim Bin Shahid, Md. Alamin Talukder, Md Ashraf Uddin
https://arxiv.org/abs/2403.05353

Hybridized Convolutional Neural Networks and Long Short-Term Memory for Improved Alzheimer's Disease Diagnosis from MRI Scans
Brain-related diseases are more sensitive than other diseases due to several factors, including the complexity of surgical procedures, high costs, and other challenges. Alzheimer's disease is a common brain disorder that causes memory loss and the shrinking of brain cells. Early detection is critical for providing proper treatment to patients. However, identifying Alzheimer's at an early stage using manual scanning of CT or MRI scans is challenging. Therefore, researchers have delved into the e…

Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks
Marco De Nadai, Francesco Fabbri, Paul Gigioli, Alice Wang, Ang Li, Fabrizio Silvestri, Laura Kim, Shawn Lin, Vladan Radosavljevic, Sandeep Ghael, David Nyhan, Hugues Bouchard, Mounia Lalmas-Roelleke, Andreas Damianou
https://arxiv.org/abs/2403.05185…

Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks
In the ever-evolving digital audio landscape, Spotify, well-known for its music and talk content, has recently introduced audiobooks to its vast user base. While promising, this move presents significant challenges for personalized recommendations. Unlike music and podcasts, audiobooks, initially available for a fee, cannot be easily skimmed before purchase, posing higher stakes for the relevance of recommendations. Furthermore, introducing a new content type into an existing platform confronts…

Efficient Sound Field Reconstruction with Conditional Invertible Neural Networks
Xenofon Karakonstantis, Efren Fernandez-Grande, Peter Gerstoft
https://arxiv.org/abs/2404.06928

Efficient Sound Field Reconstruction with Conditional Invertible Neural Networks
In this study, we introduce a method for estimating sound fields in reverberant environments using a conditional invertible neural network (CINN). Sound field reconstruction can be hindered by experimental errors, limited spatial data, model mismatches, and long inference times, leading to potentially flawed and prolonged characterizations. Further, the complexity of managing inherent uncertainties often escalates computational demands or is neglected in models. Our approach seeks to balance ac…

This https://arxiv.org/abs/2311.01385 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Ultra-Fast Generation of Air Shower Images for Imaging Air Cherenkov Telescopes using Generative Adversarial Networks
For the analysis of data taken by Imaging Air Cherenkov Telescopes (IACTs), a large number of air shower simulations are needed to derive the instrument response. The simulations are very complex, involving computational and memory-intensive calculations, and are usually performed repeatedly for different observation intervals to take into account the varying optical sensitivity of the instrument. The use of generative models based on deep neural networks offers the prospect for memory-efficien…

Beyond Gait: Learning Knee Angle for Seamless Prosthesis Control in Multiple Scenarios
Pengwei Wang, Yilong Chen, Wan Su, Jie Wang, Teng Ma, Haoyong Yu
https://arxiv.org/abs/2404.06772

Beyond Gait: Learning Knee Angle for Seamless Prosthesis Control in Multiple Scenarios
Deep learning models have become a powerful tool in knee angle estimation for lower limb prostheses, owing to their adaptability across various gait phases and locomotion modes. Current methods utilize Multi-Layer Perceptrons (MLP), Long-Short Term Memory Networks (LSTM), and Convolutional Neural Networks (CNN), predominantly analyzing motion information from the thigh. Contrary to these approaches, our study introduces a holistic perspective by integrating whole-body movements as inputs. We pr…

Are Targeted Messages More Effective?
Martin Grohe, Eran Rosenbluth
https://arxiv.org/abs/2403.06817 https://arxiv.org/pdf/2403.06817…

Are Targeted Messages More Effective?
Graph neural networks (GNN) are deep learning architectures for graphs. Essentially, a GNN is a distributed message passing algorithm, which is controlled by parameters learned from data. It operates on the vertices of a graph: in each iteration, vertices receive a message on each incoming edge, aggregate these messages, and then update their state based on their current state and the aggregated messages. The expressivity of GNNs can be characterised in terms of certain fragments of first-order…

This https://arxiv.org/abs/2303.00370 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Application of Deep Learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM TTE Data
To investigate GRBs in depth, it is crucial to develop an effective method for identifying GRBs accurately. Current criteria, e.g., onboard blind search, ground blind search, and target search, are limited by manually set thresholds and perhaps miss GRBs, especially for sub-threshold events. We propose a novel approach that utilizes convolutional neural networks (CNNs) to distinguish GRBs and non-GRBs directly. We structured three CNN models, plain-CNN, ResNet, and ResNet-CBAM, and endeavored t…

Symmetry-guided gradient descent for quantum neural networks
Kaiming Bian, Shitao Zhang, Fei Meng, Wen Zhang, Oscar Dahlsten
https://arxiv.org/abs/2404.06108

Symmetry-guided gradient descent for quantum neural networks
Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise mathematical form. We design two ways to adopt the constraints into the cost function, thereby shaping the cost landscape in favour of parameter choices which respect the given symmetry. Unlike methods that alter the neural network circuit ansatz to impose s…

Seasonal Fire Prediction using Spatio-Temporal Deep Neural Networks
Dimitrios Michail, Lefki-Ioanna Panagiotou, Charalampos Davalas, Ioannis Prapas, Spyros Kondylatos, Nikolaos Ioannis Bountos, Ioannis Papoutsis
https://arxiv.org/abs/2404.06437

Seasonal Fire Prediction using Spatio-Temporal Deep Neural Networks
With climate change expected to exacerbate fire weather conditions, the accurate anticipation of wildfires on a global scale becomes increasingly crucial for disaster mitigation. In this study, we utilize SeasFire, a comprehensive global wildfire dataset with climate, vegetation, oceanic indices, and human-related variables, to enable seasonal wildfire forecasting with machine learning. For the predictive analysis, we train deep learning models with different architectures that capture the spat…

Studying the Impact of Latent Representations in Implicit Neural Networks for Scientific Continuous Field Reconstruction
Wei Xu, Derek Freeman DeSantis, Xihaier Luo, Avish Parmar, Klaus Tan, Balu Nadiga, Yihui Ren, Shinjae Yoo
https://arxiv.org/abs/2404.06418

Studying the Impact of Latent Representations in Implicit Neural Networks for Scientific Continuous Field Reconstruction
Learning a continuous and reliable representation of physical fields from sparse sampling is challenging and it affects diverse scientific disciplines. In a recent work, we present a novel model called MMGN (Multiplicative and Modulated Gabor Network) with implicit neural networks. In this work, we design additional studies leveraging explainability methods to complement the previous experiments and further enhance the understanding of latent representations generated by the model. The adopted …

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural

(Not) Understanding Latin Poetic Style with Deep Learning
Ben Nagy
https://arxiv.org/abs/2404.06150 https://arxiv.org/pdf/2404.06150<…

(Not) Understanding Latin Poetic Style with Deep Learning
This article summarizes some mostly unsuccessful attempts to understand authorial style by examining the attention of various neural networks (LSTMs and CNNs) trained on a corpus of classical Latin verse that has been encoded to include sonic and metrical features. Carefully configured neural networks are shown to be extremely strong authorship classifiers, so it is hoped that they might therefore teach `traditional' readers something about how the authors differ in style. Sadly their reasoning…

Hybrid Training of Denoising Networks to Improve the Texture Acutance of Digital Cameras
Rapha\"el Achddou, Yann Gousseau, Sa\"id Ladjal
https://arxiv.org/abs/2404.07212

Hybrid Training of Denoising Networks to Improve the Texture Acutance of Digital Cameras
In order to evaluate the capacity of a camera to render textures properly, the standard practice, used by classical scoring protocols, is to compute the frequential response to a dead leaves image target, from which is built a texture acutance metric. In this work, we propose a mixed training procedure for image restoration neural networks, relying on both natural and synthetic images, that yields a strong improvement of this acutance metric without impairing fidelity terms. The feasibility…

GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA
Bingyi Zhang, Rajgopal Kannan, Carl Busart, Viktor Prasanna
https://arxiv.org/abs/2404.07188

GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA
Graph neural networks (GNNs) have recently empowered various novel computer vision (CV) tasks. In GNN-based CV tasks, a combination of CNN layers and GNN layers or only GNN layers are employed. This paper introduces GCV-Turbo, a domain-specific accelerator on FPGA for end-to-end acceleration of GNN-based CV tasks. GCV-Turbo consists of two key components: (1) a \emph{novel} hardware architecture optimized for the computation kernels in both CNNs and GNNs using the same set of computation resour…

This https://arxiv.org/abs/2311.00529 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A Unified Framework for the Error Analysis of Physics-Informed Neural Networks
We prove a priori and a posteriori error estimates for physics-informed neural networks (PINNs) for linear PDEs. We analyze elliptic equations in primal and mixed form, elasticity, parabolic, hyperbolic and Stokes equations; and a PDE constrained optimization problem. For the analysis, we propose an abstract framework in the common language of bilinear forms, and we show that coercivity and continuity lead to error estimates. The obtained estimates are sharp and reveal that the $L^2$ penalty ap…

This https://arxiv.org/abs/2201.09754 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deep Reinforcement Learning with Spiking Q-learning
With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (RL). There are only a few existing SNN-based RL methods at present. Most of them either lack generalization ability or employ Artificial Neural Networks (ANNs) to estimate value function in training. The former n…

Bayesian Survival Analysis by Approximate Inference of Neural Networks
Christian Marius Lillelund, Martin Magris, Christian Fischer Pedersen
https://arxiv.org/abs/2404.06421

Bayesian Survival Analysis by Approximate Inference of Neural Networks
Predicting future events always comes with uncertainty, but traditional non-Bayesian methods cannot distinguish certain from uncertain predictions or explain the confidence in their predictions. In survival analysis, Bayesian methods applied to state-of-the-art solutions in the healthcare and biomedical field are still novel, and their implications have not been fully evaluated. In this paper, we study the benefits of modeling uncertainty in deep neural networks for survival analysis with a foc…

The Ouroboros of Memristors: Neural Networks Facilitating Memristor Programming
Zhenming Yu, Ming-Jay Yang, Jan Finkbeiner, Sebastian Siegel, John Paul Strachan, Emre Neftci
https://arxiv.org/abs/2403.06712

The Ouroboros of Memristors: Neural Networks Facilitating Memristor Programming
Memristive devices hold promise to improve the scale and efficiency of machine learning and neuromorphic hardware, thanks to their compact size, low power consumption, and the ability to perform matrix multiplications in constant time. However, on-chip training with memristor arrays still faces challenges, including device-to-device and cycle-to-cycle variations, switching non-linearity, and especially SET and RESET asymmetry. To combat device non-linearity and asymmetry, we propose to program …

This https://arxiv.org/abs/2308.04179 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Breaking Speaker Recognition with PaddingBack
Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent research has shown that speech backdoors can utilize transformations as triggers, similar to image backdoors. However, human ears can easily be aware of these transformations, leading to suspicion. In this paper, we propose PaddingBack, an inaudible backdoor attack…

Symmetry-guided gradient descent for quantum neural networks
Kaiming Bian, Shitao Zhang, Fei Meng, Wen Zhang, Oscar Dahlsten
https://arxiv.org/abs/2404.06108

Symmetry-guided gradient descent for quantum neural networks
Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise mathematical form. We design two ways to adopt the constraints into the cost function, thereby shaping the cost landscape in favour of parameter choices which respect the given symmetry. Unlike methods that alter the neural network circuit ansatz to impose s…

GDR-HGNN: A Heterogeneous Graph Neural Networks Accelerator Frontend with Graph Decoupling and Recoupling
Runzhen Xue, Mingyu Yan, Dengke Han, Yihan Teng, Zhimin Tang, Xiaochun Ye, Dongrui Fan
https://arxiv.org/abs/2404.04792

GDR-HGNN: A Heterogeneous Graph Neural Networks Accelerator Frontend with Graph Decoupling and Recoupling
Heterogeneous Graph Neural Networks (HGNNs) have broadened the applicability of graph representation learning to heterogeneous graphs. However, the irregular memory access pattern of HGNNs leads to the buffer thrashing issue in HGNN accelerators. In this work, we identify an opportunity to address buffer thrashing in HGNN acceleration through an analysis of the topology of heterogeneous graphs. To harvest this opportunity, we propose a graph restructuring method and map it into a hardware front…

Stability and Performance Analysis of Discrete-Time ReLU Recurrent Neural Networks
Sahel Vahedi Noori, Bin Hu, Geir Dullerud, Peter Seiler
https://arxiv.org/abs/2405.05236

Stability and Performance Analysis of Discrete-Time ReLU Recurrent Neural Networks
This paper presents sufficient conditions for the stability and $\ell_2$-gain performance of recurrent neural networks (RNNs) with ReLU activation functions. These conditions are derived by combining Lyapunov/dissipativity theory with Quadratic Constraints (QCs) satisfied by repeated ReLUs. We write a general class of QCs for repeated RELUs using known properties for the scalar ReLU. Our stability and performance condition uses these QCs along with a "lifted" representation for the ReLU RNN. We…

This https://arxiv.org/abs/2209.05564 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deep Relaxation of Controlled Stochastic Gradient Descent via Singular Perturbations
We consider a singularly perturbed system of stochastic differential equations proposed by Chaudhari et al. (Res. Math. Sci. 2018) to approximate the Entropic Gradient Descent in the optimization of deep neural networks, via homogenisation. We embed it in a much larger class of two-scale stochastic control problems and rely on convergence results for Hamilton-Jacobi-Bellman equations with unbounded data proved recently by ourselves (ESAIM Control Optim. Calc. Var. 2023). We show that the limit …

Trials Factor for Semi-Supervised NN Classifiers in Searches for Narrow Resonances at the LHC
Benjamin Lieberman, Andreas Crivellin, Salah-Eddine Dahbi, Finn Stevenson, Nidhi Tripathi, Mukesh Kumar, Bruce Mellado
https://arxiv.org/abs/2404.07822

Trials Factor for Semi-Supervised NN Classifiers in Searches for Narrow Resonances at the LHC
To mitigate the model dependencies of searches for new narrow resonances at the Large Hadron Collider (LHC), semi-supervised Neural Networks (NNs) can be used. Unlike fully supervised classifiers these models introduce an additional look-elsewhere effect in the process of optimising thresholds on the response distribution. We perform a frequentist study to quantify this effect, in the form of a trials factor. As an example, we consider simulated $Zγ$ data to perform narrow resonance searches u…

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural

GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA
Bingyi Zhang, Rajgopal Kannan, Carl Busart, Viktor Prasanna
https://arxiv.org/abs/2404.07188

GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA
Graph neural networks (GNNs) have recently empowered various novel computer vision (CV) tasks. In GNN-based CV tasks, a combination of CNN layers and GNN layers or only GNN layers are employed. This paper introduces GCV-Turbo, a domain-specific accelerator on FPGA for end-to-end acceleration of GNN-based CV tasks. GCV-Turbo consists of two key components: (1) a \emph{novel} hardware architecture optimized for the computation kernels in both CNNs and GNNs using the same set of computation resour…

A Neuromorphic Approach to Obstacle Avoidance in Robot Manipulation
Ahmed Faisal Abdelrahman, Matias Valdenegro-Toro, Maren Bennewitz, Paul G. Pl\"oger
https://arxiv.org/abs/2404.05858

A Neuromorphic Approach to Obstacle Avoidance in Robot Manipulation
Neuromorphic computing mimics computational principles of the brain in $\textit{silico}$ and motivates research into event-based vision and spiking neural networks (SNNs). Event cameras (ECs) exclusively capture local intensity changes and offer superior power consumption, response latencies, and dynamic ranges. SNNs replicate biological neuronal dynamics and have demonstrated potential as alternatives to conventional artificial neural networks (ANNs), such as in reducing energy expenditure and…

Fair Graph Neural Network with Supervised Contrastive Regularization
Mahdi Tavassoli Kejani (UT3), Fadi Dornaika (IMT), Jean-Michel Loubes (IMT)
https://arxiv.org/abs/2404.06090 <…

Fair Graph Neural Network with Supervised Contrastive Regularization
In recent years, Graph Neural Networks (GNNs) have made significant advancements, particularly in tasks such as node classification, link prediction, and graph representation. However, challenges arise from biases that can be hidden not only in the node attributes but also in the connections between entities. Therefore, ensuring fairness in graph neural network learning has become a critical problem. To address this issue, we propose a novel model for training fairness-aware GNN, which enhances…

This https://arxiv.org/abs/2211.12971 has been replaced.
link: https://scholar.google.com/scholar?q=a

Cooperative data-driven modeling
Data-driven modeling in mechanics is evolving rapidly based on recent machine learning advances, especially on artificial neural networks. As the field matures, new data and models created by different groups become available, opening possibilities for cooperative modeling. However, artificial neural networks suffer from catastrophic forgetting, i.e. they forget how to perform an old task when trained on a new one. This hinders cooperation because adapting an existing model for a new task affec…

This https://arxiv.org/abs/2401.04956 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

EmMixformer: Mix transformer for eye movement recognition
Eye movement (EM) is a new highly secure biometric behavioral modality that has received increasing attention in recent years. Although deep neural networks, such as convolutional neural network (CNN), have recently achieved promising performance, current solutions fail to capture local and global temporal dependencies within eye movement data. To overcome this problem, we propose in this paper a mixed transformer termed EmMixformer to extract time and frequency domain information for eye movem…

This https://arxiv.org/abs/2402.16430 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Improving behavior based authentication against adversarial attack using XAI
In recent years, machine learning models, especially deep neural networks, have been widely used for classification tasks in the security domain. However, these models have been shown to be vulnerable to adversarial manipulation: small changes learned by an adversarial attack model, when applied to the input, can cause significant changes in the output. Most research on adversarial attacks and corresponding defense methods focuses only on scenarios where adversarial samples are directly generat…

Slax: A Composable JAX Library for Rapid and Flexible Prototyping of Spiking Neural Networks
Thomas M. Summe, Siddharth Joshi
https://arxiv.org/abs/2404.05807

Slax: A Composable JAX Library for Rapid and Flexible Prototyping of Spiking Neural Networks
Recent advances to algorithms for training spiking neural networks (SNNs) often leverage their unique dynamics. While backpropagation through time (BPTT) with surrogate gradients dominate the field, a rich landscape of alternatives can situate algorithms across various points in the performance, bio-plausibility, and complexity landscape. Evaluating and comparing algorithms is currently a cumbersome and error-prone process, requiring them to be repeatedly re-implemented. We introduce Slax, a JA…

This https://arxiv.org/abs/2309.06912 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Multi-behavior Recommendation with SVD Graph Neural Networks
Graph Neural Networks (GNNs) have been extensively employed in the field of recommendation systems, offering users personalized recommendations and yielding remarkable outcomes. Recently, GNNs incorporating contrastive learning have demonstrated promising performance in handling the sparse data problem of recommendation systems. However, existing contrastive learning methods still have limitations in resisting noise interference, especially for multi-behavior recommendation. To mitigate the afo…

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification
Shuai Li, Xiaoguang Ma, Shancheng Jiang, Lu Meng
https://arxiv.org/abs/2403.06798

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification
Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the A…

Qiskit-Torch-Module: Fast Prototyping of Quantum Neural Networks
Nico Meyer, Christian Ufrecht, Maniraman Periyasamy, Axel Plinge, Christopher Mutschler, Daniel D. Scherer, Andreas Maier
https://arxiv.org/abs/2404.06314

Qiskit-Torch-Module: Fast Prototyping of Quantum Neural Networks
Quantum computer simulation software is an integral tool for the research efforts in the quantum computing community. An important aspect is the efficiency of respective frameworks, especially for training variational quantum algorithms. Focusing on the widely used Qiskit software environment, we develop the qiskit-torch-module. It improves runtime performance by two orders of magnitude over comparable libraries, while facilitating low-overhead integration with existing codebases. Moreover, the…

Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Re-Training
Henrik Hose, Alexander Gr\"afe, Sebastian Trimpe
https://arxiv.org/abs/2404.05835

Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Re-Training
Model Predictive Control (MPC) is a method to control nonlinear systems with guaranteed stability and constraint satisfaction but suffers from high computation times. Approximate MPC (AMPC) with neural networks (NNs) has emerged to address this limitation, enabling deployment on resource-constrained embedded systems. However, when tuning AMPCs for real-world systems, large datasets need to be regenerated and the NN needs to be retrained at every tuning step. This work introduces a novel, parame…

This https://arxiv.org/abs/2208.07814 has been replaced.
link: https://scholar.google.com/scholar?q=a

Does Lorentz-symmetric design boost network performance in jet physics?
In the deep learning era, improving the neural network performance in jet physics is a rewarding task as it directly contributes to more accurate physics measurements at the LHC. Recent research has proposed various network designs in consideration of the full Lorentz symmetry, but its benefit is still not systematically asserted, given that there remain many successful networks without taking it into account. We conduct a detailed study on the Lorentz-symmetric design. We propose two generaliz…

This https://arxiv.org/abs/2402.06164 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAR_…

Algorithm-hardware co-design for Energy-Efficient A/D conversion in ReRAM-based accelerators
Deep neural networks are widely deployed in many fields. Due to the in-situ computation (known as processing in memory) capacity of the Resistive Random Access Memory (ReRAM) crossbar, ReRAM-based accelerator shows potential in accelerating DNN with low power and high performance. However, despite power advantage, such kind of accelerators suffer from the high power consumption of peripheral circuits, especially Analog-to-Digital Converter (ADC), which account for over 60 percent of total power…

Evolving Loss Functions for Specific Image Augmentation Techniques
Brandon Morgan, Dean Hougen
https://arxiv.org/abs/2404.06633 https://

Evolving Loss Functions for Specific Image Augmentation Techniques
Previous work in Neural Loss Function Search (NLFS) has shown a lack of correlation between smaller surrogate functions and large convolutional neural networks with massive regularization. We expand upon this research by revealing another disparity that exists, correlation between different types of image augmentation techniques. We show that different loss functions can perform well on certain image augmentation techniques, while performing poorly on others. We exploit this disparity by perfor…

DeepVM: Integrating Spot and On-Demand VMs for Cost-Efficient Deep Learning Clusters in the Cloud
Yoochan Kim, Kihyun Kim, Yonghyeon Cho, Jinwoo Kim, Awais Khan, Ki-Dong Kang, Baik-Song An, Myung-Hoon Cha, Hong-Yeon Kim, Youngjae Kim
https://arxiv.org/abs/2403.05861

DeepVM: Integrating Spot and On-Demand VMs for Cost-Efficient Deep Learning Clusters in the Cloud
Distributed Deep Learning (DDL), as a paradigm, dictates the use of GPU-based clusters as the optimal infrastructure for training large-scale Deep Neural Networks (DNNs). However, the high cost of such resources makes them inaccessible to many users. Public cloud services, particularly Spot Virtual Machines (VMs), offer a cost-effective alternative, but their unpredictable availability poses a significant challenge to the crucial checkpointing process in DDL. To address this, we introduce DeepV…

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification
Shuai Li, Xiaoguang Ma, Shancheng Jiang, Lu Meng
https://arxiv.org/abs/2403.06798

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification
Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the A…

Qiskit-Torch-Module: Fast Prototyping of Quantum Neural Networks
Nico Meyer, Christian Ufrecht, Maniraman Periyasamy, Axel Plinge, Christopher Mutschler, Daniel D. Scherer, Andreas Maier
https://arxiv.org/abs/2404.06314

Qiskit-Torch-Module: Fast Prototyping of Quantum Neural Networks
Quantum computer simulation software is an integral tool for the research efforts in the quantum computing community. An important aspect is the efficiency of respective frameworks, especially for training variational quantum algorithms. Focusing on the widely used Qiskit software environment, we develop the qiskit-torch-module. It improves runtime performance by two orders of magnitude over comparable libraries, while facilitating low-overhead integration with existing codebases. Moreover, the…

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
Maximilian Dreyer, Erblina Purelku, Johanna Vielhaben, Wojciech Samek, Sebastian Lapuschkin
https://arxiv.org/abs/2404.06453

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
The field of mechanistic interpretability aims to study the role of individual neurons in Deep Neural Networks. Single neurons, however, have the capability to act polysemantically and encode for multiple (unrelated) features, which renders their interpretation difficult. We present a method for disentangling polysemanticity of any Deep Neural Network by decomposing a polysemantic neuron into multiple monosemantic "virtual" neurons. This is achieved by identifying the relevant sub-graph ("circu…

celegansneural: C. elegans neurons (1986)
A network representing the neural connections of the Caenorhabditis elegans nematode.
This network has 297 nodes and 2359 edges.
Tags: Biological, Connectome, Weighted
https://networks.skewed.de/net/celegansneural…

CaDRec: Contextualized and Debiased Recommender Model
Xinfeng Wang, Fumiyo Fukumoto, Jin Cui, Yoshimi Suzuki, Jiyi Li, Dongjin Yu
https://arxiv.org/abs/2404.06895

CaDRec: Contextualized and Debiased Recommender Model
Recommender models aimed at mining users' behavioral patterns have raised great attention as one of the essential applications in daily life. Recent work on graph neural networks (GNNs) or debiasing methods has attained remarkable gains. However, they still suffer from (1) over-smoothing node embeddings caused by recursive convolutions with GNNs, and (2) the skewed distribution of interactions due to popularity and user-individual biases. This paper proposes a contextualized and debiased recomm…

This https://arxiv.org/abs/2304.05946 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Entanglement detection with classical deep neural networks
In this study, we introduce an autonomous method for addressing the detection and classification of quantum entanglement, a core element of quantum mechanics that has yet to be fully understood. We employ a multi-layer perceptron to effectively identify entanglement in both two- and three-qubit systems. Our technique yields impressive detection results, achieving nearly perfect accuracy for two-qubit systems and over $90\%$ accuracy for three-qubit systems. Additionally, our approach successful…

Efficient Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
A. Martina Neuman, Philipp Christian Petersen
https://arxiv.org/abs/2404.04549

Efficient Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
We study the learning problem associated with spiking neural networks. Specifically, we consider hypothesis sets of spiking neural networks with affine temporal encoders and decoders and simple spiking neurons having only positive synaptic weights. We demonstrate that the positivity of the weights continues to enable a wide range of expressivity results, including rate-optimal approximation of smooth functions or approximation without the curse of dimensionality. Moreover, positive-weight spiki…

Coupling of the Finite Element Method with Physics Informed Neural Networks for the Multi-Fluid Flow Problem
Michel Nohra, Steven Dufour
https://arxiv.org/abs/2405.05371

Coupling of the Finite Element Method with Physics Informed Neural Networks for the Multi-Fluid Flow Problem
Multi-fluid flows are found in various industrial processes, including metal injection molding and 3D printing. The accuracy of multi-fluid flow modeling is determined by how well interfaces and capillary forces are represented. In this paper, the multi-fluid flow problem is discretized using a combination of a Physics-Informed Neural Network (PINN) with a finite element discretization. To determine the best PINN formulation, a comparative study is conducted using a manufactured solution. We co…

CaDRec: Contextualized and Debiased Recommender Model
Xinfeng Wang, Fumiyo Fukumoto, Jin Cui, Yoshimi Suzuki, Jiyi Li, Dongjin Yu
https://arxiv.org/abs/2404.06895

CaDRec: Contextualized and Debiased Recommender Model
Recommender models aimed at mining users' behavioral patterns have raised great attention as one of the essential applications in daily life. Recent work on graph neural networks (GNNs) or debiasing methods has attained remarkable gains. However, they still suffer from (1) over-smoothing node embeddings caused by recursive convolutions with GNNs, and (2) the skewed distribution of interactions due to popularity and user-individual biases. This paper proposes a contextualized and debiased recomm…

Unifying Low Dimensional Observations in Deep Learning Through the Deep Linear Unconstrained Feature Model
Connall Garrod, Jonathan P. Keating
https://arxiv.org/abs/2404.06106

Unifying Low Dimensional Observations in Deep Learning Through the Deep Linear Unconstrained Feature Model
Modern deep neural networks have achieved high performance across various tasks. Recently, researchers have noted occurrences of low-dimensional structure in the weights, Hessian's, gradients, and feature vectors of these networks, spanning different datasets and architectures when trained to convergence. In this analysis, we theoretically demonstrate these observations arising, and show how they can be unified within a generalized unconstrained feature model that can be considered analytically…

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural

This https://arxiv.org/abs/2303.02797 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Variational Quantum Eigensolver for Classification in Credit Sales Risk
The data classification task is broadly utilized in numerous fields of science and it may be realized by different known approaches (e.g. neural networks). However, in this work, quantum computations were harnessed to solve the problem. We take into consideration a quantum circuit which is based on the Variational Quantum Eigensolver (VQE) and so-called SWAP-Test what allows us to solve a classification problem connected with credit sales. More specifically, we cope with a decision problem of d…

This https://arxiv.org/abs/2306.01289 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

nnMobileNe: Rethinking CNN for Retinopathy Research
Over the past few decades, convolutional neural networks (CNNs) have been at the forefront of the detection and tracking of various retinal diseases (RD). Despite their success, the emergence of vision transformers (ViT) in the 2020s has shifted the trajectory of RD model development. The leading-edge performance of ViT-based models in RD can be largely credited to their scalability-their ability to improve as more parameters are added. As a result, ViT-based models tend to outshine traditional…

Coupling of the Finite Element Method with Physics Informed Neural Networks for the Multi-Fluid Flow Problem
Michel Nohra, Steven Dufour
https://arxiv.org/abs/2405.05371

Coupling of the Finite Element Method with Physics Informed Neural Networks for the Multi-Fluid Flow Problem
Multi-fluid flows are found in various industrial processes, including metal injection molding and 3D printing. The accuracy of multi-fluid flow modeling is determined by how well interfaces and capillary forces are represented. In this paper, the multi-fluid flow problem is discretized using a combination of a Physics-Informed Neural Network (PINN) with a finite element discretization. To determine the best PINN formulation, a comparative study is conducted using a manufactured solution. We co…

This https://arxiv.org/abs/2401.11687 has been replaced.
link: https://scholar.google.com/scholar?q=a

TIM: An Efficient Temporal Interaction Module for Spiking Transformer
Spiking Neural Networks (SNNs), as the third generation of neural networks, have gained prominence for their biological plausibility and computational efficiency, especially in processing diverse datasets. The integration of attention mechanisms, inspired by advancements in neural network architectures, has led to the development of Spiking Transformers. These have shown promise in enhancing SNNs' capabilities, particularly in the realms of both static and neuromorphic datasets. Despite their p…

A Two-Stage Training Method for Modeling Constrained Systems With Neural Networks
C. Coelho, M. Fernanda P. Costa, L. L. Ferr\'as
https://arxiv.org/abs/2403.02730

A Two-Stage Training Method for Modeling Constrained Systems With Neural Networks
Real-world systems are often formulated as constrained optimization problems. Techniques to incorporate constraints into Neural Networks (NN), such as Neural Ordinary Differential Equations (Neural ODEs), have been used. However, these introduce hyperparameters that require manual tuning through trial and error, raising doubts about the successful incorporation of constraints into the generated model. This paper describes in detail the two-stage training method for Neural ODEs, a simple, effect…

This https://arxiv.org/abs/2401.11687 has been replaced.
link: https://scholar.google.com/scholar?q=a

TIM: An Efficient Temporal Interaction Module for Spiking Transformer
Spiking Neural Networks (SNNs), as the third generation of neural networks, have gained prominence for their biological plausibility and computational efficiency, especially in processing diverse datasets. The integration of attention mechanisms, inspired by advancements in neural network architectures, has led to the development of Spiking Transformers. These have shown promise in enhancing SNNs' capabilities, particularly in the realms of both static and neuromorphic datasets. Despite their p…

This https://arxiv.org/abs/2404.03425 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

ChangeMamba: Remote Sensing Change Detection with Spatio-Temporal State Space Model
Convolutional neural networks (CNN) and Transformers have made impressive progress in the field of remote sensing change detection (CD). However, both architectures have their inherent shortcomings. Recently, the Mamba architecture, based on spatial state models, has shown remarkable performance in a series of natural language processing tasks, which can effectively compensate for the shortcomings of the above two architectures. In this paper, we explore for the first time the potential of the …

Embedded Deployment of Semantic Segmentation in Medicine through Low-Resolution Inputs
Erik Ostrowski, Muhammad Shafique
https://arxiv.org/abs/2403.05340 h…

Embedded Deployment of Semantic Segmentation in Medicine through Low-Resolution Inputs
When deploying neural networks in real-life situations, the size and computational effort are often the limiting factors. This is especially true in environments where big, expensive hardware is not affordable, like in embedded medical devices, where budgets are often tight. State-of-the-art proposed multiple different lightweight solutions for such use cases, mostly by changing the base model architecture, not taking the input and output resolution into consideration. In this paper, we propose…

Neuroevolving Electronic Dynamical Networks
Derek Whitley
https://arxiv.org/abs/2404.04587 https://arxiv.org/pdf/2404.04587

Neuroevolving Electronic Dynamical Networks
Neuroevolution is a powerful method of applying an evolutionary algorithm to refine the performance of artificial neural networks through natural selection; however, the fitness evaluation of these networks can be time-consuming and computationally expensive, particularly for continuous time recurrent neural networks (CTRNNs) that necessitate the simulation of differential equations. To overcome this challenge, field programmable gate arrays (FPGAs) have emerged as an increasingly popular solut…

Deep Oscillatory Neural Network
Nurani Rajagopal Rohan, Vigneswaran C, Sayan Ghosh, Kishore Rajendran, Gaurav A, V Srinivasa Chakravarthy
https://arxiv.org/abs/2405.03725

Deep Oscillatory Neural Network
We propose a novel, brain-inspired deep neural network model known as the Deep Oscillatory Neural Network (DONN). Deep neural networks like the Recurrent Neural Networks indeed possess sequence processing capabilities but the internal states of the network are not designed to exhibit brain-like oscillatory activity. With this motivation, the DONN is designed to have oscillatory internal dynamics. Neurons of the DONN are either nonlinear neural oscillators or traditional neurons with sigmoidal o…

Hybrid Quantum Graph Neural Network for Molecular Property Prediction
Michael Vitz, Hamed Mohammadbagherpoor, Samarth Sandeep, Andrew Vlasic, Richard Padbury, Anh Pham
https://arxiv.org/abs/2405.05205

Hybrid Quantum Graph Neural Network for Molecular Property Prediction
To accelerate the process of materials design, materials science has increasingly used data driven techniques to extract information from collected data. Specially, machine learning (ML) algorithms, which span the ML discipline, have demonstrated ability to predict various properties of materials with the level of accuracy similar to explicit calculation of quantum mechanical theories, but with significantly reduced run time and computational resources. Within ML, graph neural networks have eme…

This https://arxiv.org/abs/2310.05446 has been replaced.
link: https://scholar.google.com/scholar?q=a

RetSeg: Retention-based Colorectal Polyps Segmentation Network
Vision Transformers (ViTs) have revolutionized medical imaging analysis, showcasing superior efficacy compared to conventional Convolutional Neural Networks (CNNs) in vital tasks such as polyp classification, detection, and segmentation. Leveraging attention mechanisms to focus on specific image regions, ViTs exhibit contextual awareness in processing visual data, culminating in robust and precise predictions, even for intricate medical images. Moreover, the inherent self-attention mechanism in…

This https://arxiv.org/abs/2312.01150 has been replaced.
link: https://scholar.google.com/scholar?q=a

Pointer Networks Trained Better via Evolutionary Algorithms
Pointer Network (PtrNet) is a specific neural network for solving Combinatorial Optimization Problems (COPs). While PtrNets offer real-time feed-forward inference for complex COPs instances, its quality of the results tends to be less satisfactory. One possible reason is that such issue suffers from the lack of global search ability of the gradient descent, which is frequently employed in traditional PtrNet training methods including both supervised learning and reinforcement learning. To impro…

Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods
Chenlin Zhou, Han Zhang, Liutao Yu, Yumin Ye, Zhaokun Zhou, Liwei Huang, Zhengyu Ma, Xiaopeng Fan, Huihui Zhou, Yonghong Tian
https://arxiv.org/abs/2405.04289

Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods
Spiking neural networks (SNNs) offer a promising energy-efficient alternative to artificial neural networks (ANNs), in virtue of their high biological plausibility, rich spatial-temporal dynamics, and event-driven computation. The direct training algorithms based on the surrogate gradient method provide sufficient flexibility to design novel SNN architectures and explore the spatial-temporal dynamics of SNNs. According to previous studies, the performance of models is highly dependent on their …

This https://arxiv.org/abs/2307.10974 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deep Multi-Threshold Spiking-UNet for Image Processing
U-Net, known for its simple yet efficient architecture, is widely utilized for image processing tasks and is particularly suitable for deployment on neuromorphic chips. This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating …

This https://arxiv.org/abs/2306.03623 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Spike-based computation using classical recurrent neural networks
Spiking neural networks are a type of artificial neural networks in which communication between neurons is only made of events, also called spikes. This property allows neural networks to make asynchronous and sparse computations and therefore drastically decrease energy consumption when run on specialised hardware. However, training such networks is known to be difficult, mainly due to the non-differentiability of the spike activation, which prevents the use of classical backpropagation. This …