Tootfinder

uGMM-NN: Univariate Gaussian Mixture Model Neural Network
Zakeria Sharif Ali
https://arxiv.org/abs/2509.07569 https://arxiv.org/pdf/2509.07569

uGMM-NN: Univariate Gaussian Mixture Model Neural Network
This paper introduces the Univariate Gaussian Mixture Model Neural Network (uGMM-NN), a novel neural architecture that embeds probabilistic reasoning directly into the computational units of deep networks. Unlike traditional neurons, which apply weighted sums followed by fixed nonlinearities, each uGMM-NN node parameterizes its activations as a univariate Gaussian mixture, with learnable means, variances, and mixing coefficients. This design enables richer representations by capturing multimoda…

Deep Brain Net: An Optimized Deep Learning Model for Brain tumor Detection in MRI Images Using EfficientNetB0 and ResNet50 with Transfer Learning
Daniel Onah, Ravish Desai
https://arxiv.org/abs/2507.07011

Deep Brain Net: An Optimized Deep Learning Model for Brain tumor Detection in MRI Images Using EfficientNetB0 and ResNet50 with Transfer Learning
In recent years, deep learning has shown great promise in the automated detection and classification of brain tumors from MRI images. However, achieving high accuracy and computational efficiency remains a challenge. In this research, we propose Deep Brain Net, a novel deep learning system designed to optimize performance in the detection of brain tumors. The model integrates the strengths of two advanced neural network architectures which are EfficientNetB0 and ResNet50, combined with transfer…

Hybrid Quantum Convolutional Neural Network-Aided Pilot Assignment in Cell-Free Massive MIMO Systems
Doan Hieu Nguyen, Xuan Tung Nguyen, Seon-Geun Jeong, Trinh Van Chien, Lajos Hanzo, Won Joo Hwang
https://arxiv.org/abs/2507.06585

Hybrid Quantum Convolutional Neural Network-Aided Pilot Assignment in Cell-Free Massive MIMO Systems
A sophisticated hybrid quantum convolutional neural network (HQCNN) is conceived for handling the pilot assignment task in cell-free massive MIMO systems, while maximizing the total ergodic sum throughput. The existing model-based solutions found in the literature are inefficient and/or computationally demanding. Similarly, conventional deep neural networks may struggle in the face of high-dimensional inputs, require complex architectures, and their convergence is slow due to training numerous …

Anti-Disturbance Hierarchical Sliding Mode Controller for Deep-Sea Cranes with Adaptive Control and Neural Network Compensation
Qian Zuo, Shujie Wu, Yuzhe Qian
https://arxiv.org/abs/2509.07356

Anti-Disturbance Hierarchical Sliding Mode Controller for Deep-Sea Cranes with Adaptive Control and Neural Network Compensation
To address non-linear disturbances and uncertainties in complex marine environments, this paper proposes a disturbance-resistant controller for deep-sea cranes. The controller integrates hierarchical sliding mode control, adaptive control, and neural network compensation techniques. By designing a global sliding mode surface, the dynamic coordination between the driving and non-driving subsystems is achieved, ensuring overall system stability. The subsystem surfaces reduce oscillations and enha…

NestGNN: A Graph Neural Network Framework Generalizing the Nested Logit Model for Travel Mode Choice
Yuqi Zhou, Zhanhong Cheng, Lingqian Hu, Yuheng Bu, Shenhao Wang
https://arxiv.org/abs/2509.07123

NestGNN: A Graph Neural Network Framework Generalizing the Nested Logit Model for Travel Mode Choice
Nested logit (NL) has been commonly used for discrete choice analysis, including a wide range of applications such as travel mode choice, automobile ownership, or location decisions. However, the classical NL models are restricted by their limited representation capability and handcrafted utility specification. While researchers introduced deep neural networks (DNNs) to tackle such challenges, the existing DNNs cannot explicitly capture inter-alternative correlations in the discrete choice cont…

Sharp uniform approximation for spectral Barron functions by deep neural networks
Yulei Liao, Pingbing Ming, Hao Yu
https://arxiv.org/abs/2507.06789 https:…

Sharp uniform approximation for spectral Barron functions by deep neural networks
This work explores the neural network approximation capabilities for functions within the spectral Barron space $\mathscr{B}^s$, where $s$ is the smoothness index. We demonstrate that for functions in $\mathscr{B}^{1/2}$, a shallow neural network (a single hidden layer) with $N$ units can achieve an $L^p$-approximation rate of $\mathcal{O}(N^{-1/2})$. This rate also applies to uniform approximation, differing by at most a logarithmic factor. Our results significantly reduce the smoothness requi…

DRO-EDL-MPC: Evidential Deep Learning-Based Distributionally Robust Model Predictive Control for Safe Autonomous Driving
Hyeongchan Ham, Heejin Ahn
https://arxiv.org/abs/2507.05710

DRO-EDL-MPC: Evidential Deep Learning-Based Distributionally Robust Model Predictive Control for Safe Autonomous Driving
Safety is a critical concern in motion planning for autonomous vehicles. Modern autonomous vehicles rely on neural network-based perception, but making control decisions based on these inference results poses significant safety risks due to inherent uncertainties. To address this challenge, we present a distributionally robust optimization (DRO) framework that accounts for both aleatoric and epistemic perception uncertainties using evidential deep learning (EDL). Our approach introduces a novel…

KnowIt: Deep Time Series Modeling and Interpretation
M. W. Theunissen, R. Rabe, M. H. Davel
https://arxiv.org/abs/2507.06009 https://…

KnowIt: Deep Time Series Modeling and Interpretation
KnowIt (Knowledge discovery in time series data) is a flexible framework for building deep time series models and interpreting them. It is implemented as a Python toolkit, with source code and documentation available from https://must-deep-learning.github.io/KnowIt. It imposes minimal assumptions about task specifications and decouples the definition of dataset, deep neural network architecture, and interpretability technique through well defined interfaces. This ensures the ease of importing n…

Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations
Paolo Combes, Stefan Weinzierl, Klaus Obermayer
https://arxiv.org/abs/2509.07635 htt…

Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations
Deep learning appears as an appealing solution for Automatic Synthesizer Programming (ASP), which aims to assist musicians and sound designers in programming sound synthesizers. However, integrating software synthesizers into training pipelines is challenging due to their potential non-differentiability. This work tackles this challenge by introducing a method to approximate arbitrary synthesizers. Specifically, we train a neural network to map synthesizer presets onto an audio embedding space …

Deep Feed-Forward Neural Network for Bangla Isolated Speech Recognition
Dipayan Bhadra, Mehrab Hosain, Fatema Alam
https://arxiv.org/abs/2507.07068 https:/…

Deep Feed-Forward Neural Network for Bangla Isolated Speech Recognition
As the most important human-machine interfacing tool, an insignificant amount of work has been carried out on Bangla Speech Recognition compared to the English language. Motivated by this, in this work, the performance of speaker-independent isolated speech recognition systems has been implemented and analyzed using a dataset that is created containing both isolated Bangla and English spoken words. An approach using the Mel Frequency Cepstral Coefficient (MFCC) and Deep Feed-Forward Fully Conne…

Towards In-Air Ultrasonic QR Codes: Deep Learning for Classification of Passive Reflector Constellations
Wouter Jansen, Jan Steckel
https://arxiv.org/abs/2509.06615 https://

Towards In-Air Ultrasonic QR Codes: Deep Learning for Classification of Passive Reflector Constellations
In environments where visual sensors falter, in-air sonar provides a reliable alternative for autonomous systems. While previous research has successfully classified individual acoustic landmarks, this paper takes a step towards increasing information capacity by introducing reflector constellations as encoded tags. Our primary contribution is a multi-label Convolutional Neural Network (CNN) designed to simultaneously identify multiple, closely spaced reflectors from a single in-air 3D sonar me…

From large-eddy simulations to deep learning: A U-net model for fast urban canopy flow predictions
Themistoklis Vargiemezis, Catherine Gorl\'e
https://arxiv.org/abs/2507.06533

From large-eddy simulations to deep learning: A U-net model for fast urban canopy flow predictions
Accurate prediction of wind flow fields in urban canopies is crucial for ensuring pedestrian comfort, safety, and sustainable urban design. Traditional methods using wind tunnels and Computational Fluid Dynamics, such as Large-Eddy Simulations (LES), are limited by high costs, computational demands, and time requirements. This study presents a deep neural network (DNN) approach for fast and accurate predictions of urban wind flow fields, reducing computation time from an order of 10 hours on 32…

A High-order Backpropagation Algorithm for Neural Stochastic Differential Equation Model
Daili Sheng, Minghui Song, Xiang Peng, Xuanqi Dong
https://arxiv.org/abs/2509.06292 http…

A High-order Backpropagation Algorithm for Neural Stochastic Differential Equation Model
Neural stochastic differential equation model with a Brownian motion term can capture epistemic uncertainty of deep neural network from the perspective of a dynamical system. The goal of this paper is to improve the convergence rate of the sample-wise backpropagation algorithm in neural stochastic differential equation model which has been proposed in [Archibald et al., SIAM Journal on Numerical Analysis, 62 (2024), pp. 593-621]. It is necessary to emphasize that, improving the convergence orde…

ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression
Mert Ketenci, Vincent Jeanselme, Harry Reyes Nieva, Shalmali Joshi, No\'emie Elhadad
https://arxiv.org/abs/2509.07108

ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression
Survival analysis is a fundamental tool for modeling time-to-event outcomes in healthcare. Recent advances have introduced flexible neural network approaches for improved predictive performance. However, most of these models do not provide interpretable insights into the association between exposures and the modeled outcomes, a critical requirement for decision-making in clinical practice. To address this limitation, we propose Additive Deep Hazard Analysis Mixtures (ADHAM), an interpretable ad…

TGLF-SINN: Deep Learning Surrogate Model for Accelerating Turbulent Transport Modeling in Fusion
Yadi Cao, Futian Zhang, Wesley Liu, Tom Neiser, Orso Meneghini, Lawson Fuller, Sterling Smith, Raffi Nazikian, Brian Sammuli, Rose Yu
https://arxiv.org/abs/2509.07024

TGLF-SINN: Deep Learning Surrogate Model for Accelerating Turbulent Transport Modeling in Fusion
The Trapped Gyro-Landau Fluid (TGLF) model provides fast, accurate predictions of turbulent transport in tokamaks, but whole device simulations requiring thousands of evaluations remain computationally expensive. Neural network (NN) surrogates offer accelerated inference with fully differentiable approximations that enable gradient-based coupling but typically require large training datasets to capture transport flux variations across plasma conditions, creating significant training burden and …

FACT: the Features At Convergence Theorem for neural networks
Enric Boix-Adsera, Neil Mallinar, James B. Simon, Mikhail Belkin
https://arxiv.org/abs/2507.05644

FACT: the Features At Convergence Theorem for neural networks
A central challenge in deep learning theory is to understand how neural networks learn and represent features. To this end, we prove the Features at Convergence Theorem (FACT), which gives a self-consistency equation that neural network weights satisfy at convergence when trained with nonzero weight decay. For each weight matrix $W$, this equation relates the "feature matrix" $W^\top W$ to the set of input vectors passed into the matrix during forward propagation and the loss gradients passed t…

Shared texture-like representations, not global form, underlie deep neural network alignment with human visual processing #neuroscience

Exploring a Specialized Eccentricity-Based Deep Neural Network Model to Simulate Visual Attention
Manvi Jain
https://arxiv.org/abs/2507.05031 https://

Exploring a Specialized Eccentricity-Based Deep Neural Network Model to Simulate Visual Attention
While visual attention theories abound, neurodevelopmental research remains constrained by infants' unreliable responses and limited attention spans. Through collaboration with Project Prakash, we accessed a unique population: patients gaining vision later in life. This cohort enables investigation of visual process development in cognitively mature, cooperative participants rather than infants. We collected data from pre-operation patients, post-operation patients tracked longitudinally (1, 3,…

Node-neighbor subnetworks and Hk-core decomposition
Dinghua Shi, Yang Zhao, Guanrong Chen
https://arxiv.org/abs/2507.04948 https://ar…

Node-neighbor subnetworks and Hk-core decomposition
The network homology Hk-core decomposition proposed in this article is similar to the k-core decomposition based on node degrees of the network. The C. elegans neural network and the cat cortical network are used as examples to reveal the symmetry of the deep structures of such networks. First, based on the concept of neighborhood in mathematics, some new concepts are introduced, including such as node-neighbor subnetwork and Betti numbers of the neighbor subnetwork, among others. Then, the Bet…

A Dynamical Systems Perspective on the Analysis of Neural Networks
Dennis Chemnitz, Maximilian Engel, Christian Kuehn, Sara-Viola Kuntz
https://arxiv.org/abs/2507.05164

A Dynamical Systems Perspective on the Analysis of Neural Networks
In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms. As an expository contribution we demonstrate how to re-formulate a wide variety of challenges from deep neural networks, (stochastic) gradient descent, and related topics into dynamical statements. We also tackle three concrete challenges. First, we consider the process of information propagation through a neural network, i.e., we study the input-output map for different architectures. We ex…

SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning
Hui Xie, Yuhe Liu, Shaoqi Yang, Jinyang Guo, Yufei Guo, Yuqing Ma, Jiaxin Chen, Jiaheng Liu, Xianglong Liu
https://arxiv.org/abs/2507.02945

SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning
While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable solution by reducing both parameters and synaptic operations (SynOps) to facilitate the edge deployment of SNNs, among which search-based pruning methods search for the SNNs structure after pruning. However, existing search-based methods fail to directly use SynOps as the constraint because it will d…

Intrusion Detection in Heterogeneous Networks with Domain-Adaptive Multi-Modal Learning
Mabin Umman Varghese, Zahra Taghiyarrenani
https://arxiv.org/abs/2508.03517 https://

Intrusion Detection in Heterogeneous Networks with Domain-Adaptive Multi-Modal Learning
Network Intrusion Detection Systems (NIDS) play a crucial role in safeguarding network infrastructure against cyberattacks. As the prevalence and sophistication of these attacks increase, machine learning and deep neural network approaches have emerged as effective tools for enhancing NIDS capabilities in detecting malicious activities. However, the effectiveness of traditional deep neural models is often limited by the need for extensive labelled datasets and the challenges posed by data and f…

Quantum Convolutional Neural Network with Nonlinear Effects and Barren Plateau Mitigation
Pei-Kun Yang
https://arxiv.org/abs/2508.02459 https://arxiv.org/p…

Quantum Convolutional Neural Network with Nonlinear Effects and Barren Plateau Mitigation
Quantum neural networks (QNNs) leverage quantum entanglement and superposition to enable large-scale parallel linear computation, offering a potential solution to the scalability limits of classical deep learning. However, their practical deployment is hampered by two key challenges: the lack of intrinsic nonlinear operations and the barren plateau phenomenon. We propose a quantum convolutional neural network (QCNN) architecture that simultaneously addresses both issues. Nonlinear effects are i…

The Neural Approximated Virtual Element Method for Elasticity Problems
Stefano Berrone, Moreno Pintore, Gioana Teora
https://arxiv.org/abs/2507.05786 https…

The Neural Approximated Virtual Element Method for Elasticity Problems
We present the Neural Approximated Virtual Element Method to numerically solve elasticity problems. This hybrid technique combines classical concepts from the Finite Element Method and the Virtual Element Method with recent advances in deep neural networks. Specifically, it is a polygonal method in which the virtual basis functions are element-wise approximated by a neural network, eliminating the need for stabilization or projection operators typical of the standard virtual element method. We …

Re-optimization of a deep neural network model for electron-carbon scattering using new experimental data
Beata E. Kowal, Krzysztof M. Graczyk, Artur M. Ankowski, Rwik Dharmapal Banerjee, Jose L. Bonilla, Hemant Prasad, Jan T. Sobczyk
https://arxiv.org/abs/2508.00996

Re-optimization of a deep neural network model for electron-carbon scattering using new experimental data
We present an updated deep neural network model for inclusive electron-carbon scattering. Using the bootstrap model [Phys.Rev.C 110 (2024) 2, 025501] as a prior, we incorporate recent experimental data, as well as older measurements in the deep inelastic scattering region, to derive a re-optimized posterior model. We examine the impact of these new inputs on model predictions and associated uncertainties. Finally, we evaluate the resulting cross-section predictions in the kinematic range releva…

Algebraically Observable Physics-Informed Neural Network and its Application to Epidemiological Modelling
Mizuka Komatsu
https://arxiv.org/abs/2508.04590 https://

Algebraically Observable Physics-Informed Neural Network and its Application to Epidemiological Modelling
Physics-Informed Neural Network (PINN) is a deep learning framework that integrates the governing equations underlying data into a loss function. In this study, we consider the problem of estimating state variables and parameters in epidemiological models governed by ordinary differential equations using PINNs. In practice, not all trajectory data corresponding to the population described by models can be measured. Learning PINNs to estimate the unmeasured state variables and epidemiological pa…

From Motion to Meaning: Biomechanics-Informed Neural Network for Explainable Cardiovascular Disease Identification
Comte Valentin, Gemma Piella, Mario Ceresa, Miguel A. Gonzalez Ballester
https://arxiv.org/abs/2507.05783

From Motion to Meaning: Biomechanics-Informed Neural Network for Explainable Cardiovascular Disease Identification
Cardiac diseases are among the leading causes of morbidity and mortality worldwide, which requires accurate and timely diagnostic strategies. In this study, we introduce an innovative approach that combines deep learning image registration with physics-informed regularization to predict the biomechanical properties of moving cardiac tissues and extract features for disease classification. We utilize the energy strain formulation of Neo-Hookean material to model cardiac tissue deformations, opti…

Deep Neural Network-Driven Adaptive Filtering
Qizhen Wang, Gang Wang, Ying-Chang Liang
https://arxiv.org/abs/2508.04258 https://arxiv.org/pdf/2508.04258

Deep Neural Network-Driven Adaptive Filtering
This paper proposes a deep neural network (DNN)-driven framework to address the longstanding generalization challenge in adaptive filtering (AF). In contrast to traditional AF frameworks that emphasize explicit cost function design, the proposed framework shifts the paradigm toward direct gradient acquisition. The DNN, functioning as a universal nonlinear operator, is structurally embedded into the core architecture of the AF system, establishing a direct mapping between filtering residuals and…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[6/6]:
- Supervised Dynamic Dimension Reduction with Deep Neural Network
Zhanye Luo, Yuefeng Han, Xiufan Yu

A Comparative Study of Optimal Control and Neural Networks in Asteroid Rendezvous Mission Analysis
Zhong Zhang, Niccol\`o Michelotti, Gon\c{c}alo Oliveira Pinho, Francesco Topputo
https://arxiv.org/abs/2508.02920

A Comparative Study of Optimal Control and Neural Networks in Asteroid Rendezvous Mission Analysis
This paper presents a comparative study of the applicability and accuracy of optimal control methods and neural network-based estimators in the context of porkchop plots for preliminary asteroid rendezvous mission design. The scenario considered involves a deep-space CubeSat equipped with a low-thrust engine, departing from Earth and rendezvousing with a near-Earth asteroid within a three-year launch window. A low-thrust trajectory optimization model is formulated, incorporating variable specif…

Fredholm Neural Networks for forward and inverse problems in elliptic PDEs
Kyriakos Georgiou, Constantinos Siettos, Athanasios N. Yannacopoulos
https://arxiv.org/abs/2507.06038

Fredholm Neural Networks for forward and inverse problems in elliptic PDEs
Building on our previous work introducing Fredholm Neural Networks (Fredholm NNs/ FNNs) for solving integral equations, we extend the framework to tackle forward and inverse problems for linear and semi-linear elliptic partial differential equations. The proposed scheme consists of a deep neural network (DNN) which is designed to represent the iterative process of fixed-point iterations for the solution of elliptic PDEs using the boundary integral method within the framework of potential theory…

Unsupervised learning for inverse problems in computed tomography
Laura Hellwege, Johann Christopher Engster, Moritz Schaar, Thorsten M. Buzug, Maik Stille
https://arxiv.org/abs/2508.05321

Unsupervised learning for inverse problems in computed tomography
This study presents an unsupervised deep learning approach for computed tomography (CT) image reconstruction, leveraging the inherent similarities between deep neural network training and conventional iterative reconstruction methods. By incorporating forward and backward projection layers within the deep learning framework, we demonstrate the feasibility of reconstructing images from projection data without relying on ground-truth images. Our method is evaluated on the two-dimensional 2DeteCT …

Fine-tuning physics-informed neural networks for cavity flows using coordinate transformation
Ryuta Takao, Satoshi Ii
https://arxiv.org/abs/2508.01122 https://

Fine-tuning physics-informed neural networks for cavity flows using coordinate transformation
Physics-informed neural networks (PINNs) have attracted attention as an alternative approach to solve partial differential equations using a deep neural network (DNN). Their simplicity and capability allow them to solve inverse problems for many applications. Despite the versatility of PINNs, it remains challenging to reduce their training cost. Using a DNN pre-trained with an arbitrary dataset with transfer learning or fine-tuning is a potential solution. However, a pre-trained model using a d…

MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices
Hailong Yan, Ao Li, Xiangtao Zhang, Zhe Liu, Zenglin Shi, Ce Zhu, Le Zhang
https://arxiv.org/abs/2507.01838

MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices
Recent advancements in deep neural networks have driven significant progress in image enhancement (IE). However, deploying deep learning models on resource-constrained platforms, such as mobile devices, remains challenging due to high computation and memory demands. To address these challenges and facilitate real-time IE on mobile, we introduce an extremely lightweight Convolutional Neural Network (CNN) framework with around 4K parameters. Our approach integrates reparameterization with an Incr…

A Novel Active Learning Approach to Label One Million Unknown Malware Variants
Ahmed Bensaoud, Jugal Kalita
https://arxiv.org/abs/2507.02959 https://

A Novel Active Learning Approach to Label One Million Unknown Malware Variants
Active learning for classification seeks to reduce the cost of labeling samples by finding unlabeled examples about which the current model is least certain and sending them to an annotator/expert to label. Bayesian theory can provide a probabilistic view of deep neural network models by asserting a prior distribution over model parameters and estimating the uncertainties by posterior distribution over these parameters. This paper proposes two novel active learning approaches to label one milli…

IP-Basis PINNs: Efficient Multi-Query Inverse Parameter Estimation
Shalev Manor, Mohammad Kohandel
https://arxiv.org/abs/2509.07245 https://arxiv.org/pdf/2…

IP-Basis PINNs: Efficient Multi-Query Inverse Parameter Estimation
Solving inverse problems with Physics-Informed Neural Networks (PINNs) is computationally expensive for multi-query scenarios, as each new set of observed data requires a new, expensive training procedure. We present Inverse-Parameter Basis PINNs (IP-Basis PINNs), a meta-learning framework that extends the foundational work of Desai et al. (2022) to enable rapid and efficient inference for inverse problems. Our method employs an offline-online decomposition: a deep network is first trained offl…

Dynamic Slimmable Networks for Efficient Speech Separation
Mohamed Elminshawi, Srikanth Raj Chetupalli, Emanu\"el A. P. Habets
https://arxiv.org/abs/2507.06179

Dynamic Slimmable Networks for Efficient Speech Separation
Recent progress in speech separation has been largely driven by advances in deep neural networks, yet their high computational and memory requirements hinder deployment on resource-constrained devices. A significant inefficiency in conventional systems arises from using static network architectures that maintain constant computational complexity across all input segments, regardless of their characteristics. This approach is sub-optimal for simpler segments that do not require intensive process…

Deep Learning for Operational High-Resolution Nowcasting in Switzerland Using Graph Neural Networks
Oph\'elia Miralles, Daniele Nerini, Jonas Bhend, Baudouin Raoult, Christoph Spirig
https://arxiv.org/abs/2509.00017

Deep Learning for Operational High-Resolution Nowcasting in Switzerland Using Graph Neural Networks
Recent advances in neural weather forecasting have shown significant potential for accurate short-term forecasts. However, adapting such gridded approaches to smaller, topographically complex regions like Switzerland introduces computational challenges, especially when aiming for high spatial (1 km) and temporal (10 minutes) resolution. This paper presents a Graph Neural Network (GNN)-based approach for high-resolution nowcasting in Switzerland using the Anemoi framework and observational input…

Deep Feature-specific Imaging
Yizhou Lu
https://arxiv.org/abs/2508.01981 https://arxiv.org/pdf/2508.01981

Deep Feature-specific Imaging
Modern photon-counting sensors are increasingly dominated by Poisson noise, yet conventional Feature-Specific Imaging (FSI) is optimized for additive Gaussian noise, leading to suboptimal performance and a loss of its advantages under Poisson noise. To address this, we introduce DeepFSI, a novel end-to-end optical-electronic framework. DeepFSI "unfreezes" traditional FSI masks, enabling a deep neural network to learn globally optimal measurement masks by computing gradients directly under reali…

FLARE: A Dataflow-Aware and Scalable Hardware Architecture for Neural-Hybrid Scientific Lossy Compression
Wenqi Jia, Ying Huang, Jian Xu, Zhewen Hu, Sian Jin, Jiannan Tian, Yuede Ji, Miao Yin
https://arxiv.org/abs/2507.01224

FLARE: A Dataflow-Aware and Scalable Hardware Architecture for Neural-Hybrid Scientific Lossy Compression
Scientific simulation leveraging high-performance computing (HPC) systems is crucial for modeling complex systems and phenomena in fields such as astrophysics, climate science, and fluid dynamics, generating massive datasets that often reach petabyte to exabyte scales. However, managing these vast data volumes introduces significant I/O and network bottlenecks, limiting practical performance and scalability. While cutting-edge lossy compression frameworks powered by deep neural networks (DNNs) …

Supervised Dynamic Dimension Reduction with Deep Neural Network
Zhanye Luo, Yuefeng Han, Xiufan Yu
https://arxiv.org/abs/2508.03546 https://arxiv.org/pdf/2…

Supervised Dynamic Dimension Reduction with Deep Neural Network
This paper studies the problem of dimension reduction, tailored to improving time series forecasting with high-dimensional predictors. We propose a novel Supervised Deep Dynamic Principal component analysis (SDDP) framework that incorporates the target variable and lagged observations into the factor extraction process. Assisted by a temporal neural network, we construct target-aware predictors by scaling the original predictors in a supervised manner, with larger weights assigned to predictors…

Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach
Obasho M, Shambhavi Jaiswal, Santanu Das, Krishna Mohan Parattu
https://arxiv.org/abs/2509.00139

Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach
Extracting cosmological information from microwave sky observations requires accurate estimation of the underlying Cosmic Microwave Background (CMB) by removing foreground contamination, instrumental noise, and the effects of beam convolution. In this work, we develop a machine learning-based approach for CMB reconstruction using a generative adversarial network (GAN) architecture, where the generator is modeled as a U-Net-based convolutional neural network. To train the network, we generate …

Deep Complex-valued Neural-Network Modeling and Optimization of Stacked Intelligent Surfaces
Abdullah Zayat, Omran Abbas, Loic Markley, Anas Chaaban
https://arxiv.org/abs/2509.00340

Deep Complex-valued Neural-Network Modeling and Optimization of Stacked Intelligent Surfaces
We propose a complex-valued neural-network (CV-NN) framework to optimally configure stacked intelligent surfaces (SIS) in next-generation multi-antenna systems. Unlike conventional solutions that separately tune analog metasurface phases or rely strictly on SVD-based orthogonal decompositions, our method models each SIS element as a unit-modulus complex-velued neuron in an end-to-end differentiable pipeline. This approach avoids enforcing channel orthogonality and instead allows for richer wave…

Double descent: When do neural quantum states generalize?
M. Schuyler Moss, Alev Orfi, Christopher Roth, Anirvan M. Sengupta, Antoine Georges, Dries Sels, Anna Dawid, Agnes Valenti
https://arxiv.org/abs/2508.00068

Double descent: When do neural quantum states generalize?
Neural quantum states (NQS) provide flexible wavefunction parameterizations for numerical studies of quantum many-body physics. While inspired by deep learning, it remains unclear to what extent NQS share characteristics with neural networks used for standard machine learning tasks. We demonstrate that NQS exhibit the double descent phenomenon, a key feature of modern deep learning, where generalization worsens as network size increases before improving again in an overparameterized regime. Not…

EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer
Ranyang Zhou, Abeer Matar A. Almalky, Gamana Aragonda, Sabbir Ahmed, Filip Roth Tr{\o}nnes-Christensen, Adnan Siraj Rakin, Shaahin Angizi
https://arxiv.org/abs/2507.02206 …

EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer
True Random Number Generators (TRNGs) play a fundamental role in hardware security, cryptographic systems, and data protection. In the context of Deep NeuralNetworks (DNNs), safeguarding model parameters, particularly weights, is critical to ensure the integrity, privacy, and intel-lectual property of AI systems. While software-based pseudo-random number generators are widely used, they lack the unpredictability and resilience offered by hardware-based TRNGs. In this work, we propose a novel an…

Decentralised self-organisation of pivoting cube ensembles using geometric deep learning
Nadezhda Dobreva, Emmanuel Blazquez, Jai Grover, Dario Izzo, Yuzhen Qin, Dominik Dold
https://arxiv.org/abs/2509.03140

Decentralised self-organisation of pivoting cube ensembles using geometric deep learning
We present a decentralized model for autonomous reconfiguration of homogeneous pivoting cube modular robots in two dimensions. Each cube in the ensemble is controlled by a neural network that only gains information from other cubes in its local neighborhood, trained using reinforcement learning. Furthermore, using geometric deep learning, we include the grid symmetries of the cube ensemble in the neural network architecture. We find that even the most localized versions succeed in reconfiguring…

Tunable Wavelet Unit based Convolutional Neural Network in Optical Coherence Tomography Analysis Enhancement for Classifying Type of Epiretinal Membrane Surgery
An Le, Nehal Mehta, William Freeman, Ines Nagel, Melanie Tran, Anna Heinke, Akshay Agnihotri, Lingyun Cheng, Dirk-Uwe Bartsch, Hung Nguyen, Truong Nguyen, Cheolhong An
https://

Tunable Wavelet Unit based Convolutional Neural Network in Optical Coherence Tomography Analysis Enhancement for Classifying Type of Epiretinal Membrane Surgery
In this study, we developed deep learning-based method to classify the type of surgery performed for epiretinal membrane (ERM) removal, either internal limiting membrane (ILM) removal or ERM-alone removal. Our model, based on the ResNet18 convolutional neural network (CNN) architecture, utilizes postoperative optical coherence tomography (OCT) center scans as inputs. We evaluated the model using both original scans and scans preprocessed with energy crop and wavelet denoising, achieving 72% acc…

Comparison between Supervised and Unsupervised Learning in Deep Unfolded Sparse Signal Recovery
Koshi Nagahisa, Ryo Hayakawa, Youji Iiguni
https://arxiv.org/abs/2509.01331 https…

Comparison between Supervised and Unsupervised Learning in Deep Unfolded Sparse Signal Recovery
This paper investigates the impact of loss function selection in deep unfolding techniques for sparse signal recovery algorithms. Deep unfolding transforms iterative optimization algorithms into trainable lightweight neural networks by unfolding their iterations as network layers, with various loss functions employed for parameter learning depending on application contexts. We focus on deep unfolded versions of the fundamental iterative shrinkage thresholding algorithm (ISTA) and the iterative …

Reducing Data Requirements for Sequence-Property Prediction in Copolymer Compatibilizers via Deep Neural Network Tuning
Md Mushfiqul Islam, Nishat N. Labiba, Lawrence O. Hall, David S. Simmons
https://arxiv.org/abs/2507.21902

Reducing Data Requirements for Sequence-Property Prediction in Copolymer Compatibilizers via Deep Neural Network Tuning
Synthetic sequence-controlled polymers promise to transform polymer science by combining the chemical versatility of synthetic polymers with the precise sequence-mediated functionality of biological proteins. However, design of these materials has proven extraordinarily challenging, because they lack the massive datasets of closely related evolved molecules that accelerate design of proteins. Here we report on a new Artifical Intelligence strategy to dramatically reduce the amount of data neces…

Bit Transition Reduction by Data Transmission Ordering in NoC-based DNN Accelerator
Yizhi Chen, Jingwei Li, Wenyao Zhu, Zhonghai Lu
https://arxiv.org/abs/2509.00500 https://

Bit Transition Reduction by Data Transmission Ordering in NoC-based DNN Accelerator
As Deep Neural Networks (DNN) are becoming essential, Network-on-Chip (NoC)-based DNN accelerators gained increasing popularity. To save link power in NoC, many researchers focus on reducing the Bit Transition (BT). We propose '1'-bit count-based ordering method to reduce BT for DNN workloads. We provide a mathematical proof of the efficacy of proposed ordering. We evaluate our method through experiments without NoC and with NoC. Without NoC, our proposed ordering method achieves up to 20.38% B…

Generating Large Semi-Synthetic Graphs of Any Size
Rodrigo Tuna, Carlos Soares
https://arxiv.org/abs/2507.02166 https://arxiv.org/pdf…

Generating Large Semi-Synthetic Graphs of Any Size
Graph generation is an important area in network science. Traditional approaches focus on replicating specific properties of real-world graphs, such as small diameters or power-law degree distributions. Recent advancements in deep learning, particularly with Graph Neural Networks, have enabled data-driven methods to learn and generate graphs without relying on predefined structural properties. Despite these advances, current models are limited by their reliance on node IDs, which restricts thei…

Segmenting proto-halos with vision transformers
Toka Alokda, Cristiano Porciani
https://arxiv.org/abs/2508.00049 https://arxiv.org/pdf/2508.00049

Segmenting proto-halos with vision transformers
The formation of dark-matter halos from small cosmological perturbations generated in the early universe is a highly non-linear process typically modeled through N-body simulations. In this work, we explore the use of deep learning to segment and classify proto-halo regions in the initial density field according to their final halo mass at redshift $z=0$. We compare two architectures: a fully convolutional neural network (CNN) based on the V-Net design and a U-Net transformer. We find that the …

Accurate and scalable deep Maxwell solvers using multilevel iterative methods
Chenkai Mao, Jonathan A. Fan
https://arxiv.org/abs/2509.03622 https://arxiv.o…

Accurate and scalable deep Maxwell solvers using multilevel iterative methods
Neural networks have promise as surrogate partial differential equation (PDE) solvers, but it remains a challenge to use these concepts to solve problems with high accuracy and scalability. In this work, we show that neural network surrogates can combine with iterative algorithms to accurately solve PDE problems featuring different scales, resolutions, and boundary conditions. We develop a subdomain neural operator model that supports arbitrary Robin-type boundary condition inputs, and we show …

Causal Spatial Quantile Regression
Yan Gong, Reetam Majumder, Brian J. Reich, Rapha\"el Huser
https://arxiv.org/abs/2509.02294 https://arxiv.org/pdf/2…

Causal Spatial Quantile Regression
Treatment effects in a wide range of economic, environmental, and epidemiological applications often vary across space, and understanding the heterogeneity of causal effects across space and outcome quantiles is a critical challenge in spatial causal inference. To effectively capture spatial heterogeneity in distributional treatment effects, we propose a novel semiparametric neural network-based causal framework leveraging deep spatial quantile regression and then construct a plug-in estimator …

Adaptive AI Model Partitioning over 5G Networks
Tam Thanh Nguyen, Tuan Van Ngo, Long Thanh Le, Yong Hao Pua, Mao Van Ngo, Binbin Chen, Tony Q. S. Quek
https://arxiv.org/abs/2509.01906

Adaptive AI Model Partitioning over 5G Networks
Mobile devices increasingly rely on deep neural networks (DNNs) for complex inference tasks, but running entire models locally drains the device battery quickly. Offloading computation entirely to cloud or edge servers reduces processing load at devices but poses privacy risks and can incur high network bandwidth consumption and long delays. Split computing (SC) mitigates these challenges by partitioning DNNs between user equipment (UE) and edge servers. However, 5G wireless channels are time-v…

EZhouNet:A framework based on graph neural network and anchor interval for the respiratory sound event detection
Yun Chu, Qiuhao Wang, Enze Zhou, Qian Liu, Gang Zheng
https://arxiv.org/abs/2509.01153

EZhouNet:A framework based on graph neural network and anchor interval for the respiratory sound event detection
Auscultation is a key method for early diagnosis of respiratory and pulmonary diseases, relying on skilled healthcare professionals. However, the process is often subjective, with variability between experts. As a result, numerous deep learning-based automatic classification methods have emerged, most of which focus on respiratory sound classification. In contrast, research on respiratory sound event detection remains limited. Existing sound event detection methods typically rely on frame-level…

Template-Fitting Meets Deep Learning: Redshift Estimation Using Physics-Guided Neural Networks
Jonas Chris Ferrao, Dickson Dias, Pranav Naik, Glory D'Cruz, Anish Naik, Siya Khandeparkar, Manisha Gokuldas Fal Dessai
https://arxiv.org/abs/2507.00866

Template-Fitting Meets Deep Learning: Redshift Estimation Using Physics-Guided Neural Networks
Accurate photometric redshift estimation is critical for observational cosmology, especially in large-scale surveys where spectroscopic measurements are impractical. Traditional approaches include template fitting and machine learning, each with distinct strengths and limitations. We present a hybrid method that integrates template fitting with deep learning using physics-guided neural networks. By embedding spectral energy distribution templates into the network architecture, our model encodes…

Uncertainty Quantification for Large-Scale Deep Networks via Post-StoNet Modeling
Yan Sun, Faming Liang
https://arxiv.org/abs/2508.01217 https://arxiv.org/…

Uncertainty Quantification for Large-Scale Deep Networks via Post-StoNet Modeling
Deep learning has revolutionized modern data science. However, how to accurately quantify the uncertainty of predictions from large-scale deep neural networks (DNNs) remains an unresolved issue. To address this issue, we introduce a novel post-processing approach. This approach feeds the output from the last hidden layer of a pre-trained large-scale DNN model into a stochastic neural network (StoNet), then trains the StoNet with a sparse penalty on a validation dataset and constructs prediction…

ARDO: A Weak Formulation Deep Neural Network Method for Elliptic and Parabolic PDEs Based on Random Differences of Test Functions
Wei Cai, Andrew Qing He
https://arxiv.org/abs/2509.03757

ARDO: A Weak Formulation Deep Neural Network Method for Elliptic and Parabolic PDEs Based on Random Differences of Test Functions
We propose ARDO method for solving PDEs and PDE-related problems with deep learning techniques. This method uses a weak adversarial formulation but transfers the random difference operator onto the test function. The main advantage of this framework is that it is fully derivative-free with respect to the solution neural network. This framework is particularly suitable for Fokker-Planck type second-order elliptic and parabolic PDEs.

DeepQuark: deep-neural-network approach to multiquark bound states
Wei-Lin Wu, Lu Meng, Shi-Lin Zhu
https://arxiv.org/abs/2506.20555 https://

DeepQuark: deep-neural-network approach to multiquark bound states
For the first time, we implement the deep-neural-network-based variational Monte Carlo approach for the multiquark bound states, whose complexity surpasses that of electron or nucleon systems due to strong SU(3) color interactions. We design a novel and high-efficiency architecture, DeepQuark, to address the unique challenges in multiquark systems such as stronger correlations, extra discrete quantum numbers, and intractable confinement interaction. Our method demonstrates competitive performan…

Aleatoric Uncertainty from AI-based 6D Object Pose Predictors for Object-relative State Estimation
Thomas Jantos, Stephan Weiss, Jan Steinbrener
https://arxiv.org/abs/2509.01583

Aleatoric Uncertainty from AI-based 6D Object Pose Predictors for Object-relative State Estimation
Deep Learning (DL) has become essential in various robotics applications due to excelling at processing raw sensory data to extract task specific information from semantic objects. For example, vision-based object-relative navigation relies on a DL-based 6D object pose predictor to provide the relative pose between the object and the robot as measurements to the robot's state estimator. Accurately knowing the uncertainty inherent in such Deep Neural Network (DNN) based measurements is essential…

Classification based deep learning models for lung cancer and disease using medical images
Ahmad Chaddad, Jihao Peng, Yihang Wu
https://arxiv.org/abs/2507.01279

Classification based deep learning models for lung cancer and disease using medical images
The use of deep learning (DL) in medical image analysis has significantly improved the ability to predict lung cancer. In this study, we introduce a novel deep convolutional neural network (CNN) model, named ResNet+, which is based on the established ResNet framework. This model is specifically designed to improve the prediction of lung cancer and diseases using the images. To address the challenge of missing feature information that occurs during the downsampling process in CNNs, we integrate …

Deep Tangent Bundle (DTB) method: a Deep Neural Network approach to compute solutions of PDES
Hao Wu, Haomin Zhou
https://arxiv.org/abs/2509.00957 https://…

Deep Tangent Bundle (DTB) method: a Deep Neural Network approach to compute solutions of PDES
We develop a numerical framework, the Deep Tangent Bundle (DTB) method, that is suitable for computing solutions of evolutionary partial differential equations (PDEs) in high dimensions. The main idea is to use the tangent bundle of an adaptively updated deep neural network (DNN) to approximate the vector field in the spatial variables while applying the traditional schemes for time discretization. The DTB method takes advantage of the expression power of DNNs and the simplicity of the tangent …

Deep Neuro-Adaptive Sliding Mode Controller for Higher-Order Heterogeneous Nonlinear Multi-Agent Teams with Leader
Khushal Chaudhari, Krishanu Nath, Manas Kumar Bera
https://arxiv.org/abs/2507.21667

Deep Neuro-Adaptive Sliding Mode Controller for Higher-Order Heterogeneous Nonlinear Multi-Agent Teams with Leader
This letter proposes a deep neural network (DNN)-based neuro-adaptive sliding mode control (SMC) strategy for leader-follower tracking in multi-agent systems with higher-order, heterogeneous, nonlinear, and unknown dynamics under external disturbances. The DNN is used to compensate the unknown nonlinear dynamics with higher accuracy than shallow neural networks (NNs) and SMC ensures robust tracking. This framework employs restricted potential functions within a set-theoretic paradigm to ensure …

Hierarchical Graph Neural Network for Compressed Speech Steganalysis
Mustapha Hemis, Hamza Kheddar, Mohamed Chahine Ghanem, Bachir Boudraa
https://arxiv.org/abs/2507.21591 https…

Hierarchical Graph Neural Network for Compressed Speech Steganalysis
Steganalysis methods based on deep learning (DL) often struggle with computational complexity and challenges in generalizing across different datasets. Incorporating a graph neural network (GNN) into steganalysis schemes enables the leveraging of relational data for improved detection accuracy and adaptability. This paper presents the first application of a Graph Neural Network (GNN), specifically the GraphSAGE architecture, for steganalysis of compressed voice over IP (VoIP) speech streams. Th…

Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns
Konstantinos Drossos, Mikko Heikkinen, Paschalis Tsiaflakis
https://arxiv.org/abs/2509.05079

Lightweight DNN for Full-Band Speech Denoising on Mobile Devices: Exploiting Long and Short Temporal Patterns
Speech denoising (SD) is an important task of many, if not all, modern signal processing chains used in devices and for everyday-life applications. While there are many published and powerful deep neural network (DNN)-based methods for SD, few are optimized for resource-constrained platforms such as mobile devices. Additionally, most DNN-based methods for SD are not focusing on full-band (FB) signals, i.e. having 48 kHz sampling rate, and/or low latency cases. In this paper we present a causal,…

Data-Driven Surrogate Modeling of DSMC Solutions Using Deep Neural Networks
Ehsan Roohi, Ahmad Shoja-sani
https://arxiv.org/abs/2506.22453 https://

Data-Driven Surrogate Modeling of DSMC Solutions Using Deep Neural Networks
This study presents a deep neural network (DNN) framework that accelerates Direct Simulation Monte Carlo (DSMC) computations for rarefied-gas flows, while maintaining high physical fidelity. First, a fully connected deep neural network is trained on high-quality DSMC data for seven temperatures (200-650 K) to reproduce the Maxwell-Boltzmann speed distribution of argon. Injecting the physical boundary point into the training set enforces the correct low-speed limit. It reduces the mean-squared e…

Analyzing partially-polarized light with a photonic deep random neural network
Alessandro Petrini, Claudio Conti, Davide Pierangeli
https://arxiv.org/abs/2506.17952

Analyzing partially-polarized light with a photonic deep random neural network
Optical neural networks are emerging as a powerful and versatile tool for processing optical signals directly in the optical domain with superior speed, integrability, and functionality. Their application to optical polarization enables neuromorphic polarization sensors, but their operation is limited to fully-polarized light. Here, we demonstrate single-shot analysis of partially-polarized beams with a photonic random neural network (PRNN). The PRNN is composed of a series of optical layers im…

Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition
Sarah Seifi, Tobias Sukianto, Cecilia Carbonelli, Lorenzo Servadei, Robert Wille
https://arxiv.org/abs/2506.22443

Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition
Rule-based models offer interpretability but struggle with complex data, while deep neural networks excel in performance yet lack transparency. This work investigates a neuro-symbolic rule learning neural network named RL-Net that learns interpretable rule lists through neural optimization, applied for the first time to radar-based hand gesture recognition (HGR). We benchmark RL-Net against a fully transparent rule-based system (MIRA) and an explainable black-box model (XentricAI), evaluating a…

A Convolutional Hierarchical Deep-learning Neural Network (C-HiDeNN) Framework for Non-linear Finite Element/Meshfree Analysis
Yingjian Liu, Monish Yadav Pabbala, Jiachen Guo, Chanwook Park, Gino Domel, Wing Kam Liu, Dong Qian
https://arxiv.org/abs/2509.02435

A Convolutional Hierarchical Deep-learning Neural Network (C-HiDeNN) Framework for Non-linear Finite Element/Meshfree Analysis
We present a framework for the Convolutional Hierarchical Deep Neural Network (C-HiDeNN) tailored for nonlinear finite element and meshfree analysis. Building upon the structured foundation of HiDeNN, which includes the evaluation of shape function derivatives, adaptivity, and material derivatives, C-HiDeNN introduces a convolution operator to enhance the HiDeNN approximation. A distinctive feature of C-HiDeNN is its expanded set of optimization parameters, such as the polynomial order 'p,' dil…

Dispatch-Aware Deep Neural Network for Optimal Transmission Switching: Toward Real-Time and Feasibility Guaranteed Operation
Minsoo Kim, Jip Kim
https://arxiv.org/abs/2507.17194

Dispatch-Aware Deep Neural Network for Optimal Transmission Switching: Toward Real-Time and Feasibility Guaranteed Operation
Optimal transmission switching (OTS) improves optimal power flow (OPF) by selectively opening transmission lines, but its mixed-integer formulation increases computational complexity, especially on large grids. To deal with this, we propose a dispatch-aware deep neural network (DA-DNN) that accelerates DC-OTS without relying on pre-solved labels. DA-DNN predicts line states and passes them through a differentiable DC-OPF layer, using the resulting generation cost as the loss function so that al…

Surrogate-Assisted Evolution for Efficient Multi-branch Connection Design in Deep Neural Networks
Fergal Stapleton, Daniel Garc\'ia N\'u\~nez, Yanan Sun, Edgar Galv\'an
https://arxiv.org/abs/2506.20469

Surrogate-Assisted Evolution for Efficient Multi-branch Connection Design in Deep Neural Networks
State-of-the-art Deep Neural Networks (DNNs) often incorporate multi-branch connections, enabling multi-scale feature extraction and enhancing the capture of diverse features. This design improves network capacity and generalisation to unseen data. However, training such DNNs can be computationally expensive. The challenge is further exacerbated by the complexity of identifying optimal network architectures. To address this, we leverage Evolutionary Algorithms (EAs) to automatically discover hi…

Solving two and three-body systems with deep neural networks
Ruitian Li, Xuan Luo, Hao Sun, Pablo G. Ortega
https://arxiv.org/abs/2507.17559 https://

Solving two and three-body systems with deep neural networks
We develop a new method for solving two- and three-body bound state problems using unsupervised machine learning techniques. We use a deep neural network to calculate both simple and realistic potentials, obtaining the properties of the deuteron and triton bound states for the chiral effective field theory NN potential. Our results provide significant accuracy with no prior assumptions about the behaviour of the wave function. This neural network technique, which extends from two-body to three-…

Automated anatomy-based post-processing reduces false positives and improved interpretability of deep learning intracranial aneurysm detection
Jisoo Kim, Chu-Hsuan Lin, Alberto Ceballos-Arroyo, Ping Liu, Huaizu Jiang, Shrikanth Yadav, Qi Wan, Lei Qin, Geoffrey S Young
https://arxiv.org/abs/2507.00832

Automated anatomy-based post-processing reduces false positives and improved interpretability of deep learning intracranial aneurysm detection
Introduction: Deep learning (DL) models can help detect intracranial aneurysms on CTA, but high false positive (FP) rates remain a barrier to clinical translation, despite improvement in model architectures and strategies like detection threshold tuning. We employed an automated, anatomy-based, heuristic-learning hybrid artery-vein segmentation post-processing method to further reduce FPs. Methods: Two DL models, CPM-Net and a deformable 3D convolutional neural network-transformer hybrid (3D-CN…

Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
David Holzm\"uller, Max Sch\"olpple
https://arxiv.org/abs/2506.22429 …

Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
While the theory of deep learning has made some progress in recent years, much of it is limited to the ReLU activation function. In particular, while the neural tangent kernel (NTK) and neural network Gaussian process kernel (NNGP) have given theoreticians tractable limiting cases of fully connected neural networks, their properties for most activation functions except for powers of the ReLU function are poorly understood. Our main contribution is to provide a more general characterization of t…

A segmented robot grasping perception neural network for edge AI
Casper Br\"ocheler, Thomas Vroom, Derrick Timmermans, Alan van den Akker, Guangzhi Tang, Charalampos S. Kouzinopoulos, Rico M\"ockel
https://arxiv.org/abs/2507.13970

A segmented robot grasping perception neural network for edge AI
Robotic grasping, the ability of robots to reliably secure and manipulate objects of varying shapes, sizes and orientations, is a complex task that requires precise perception and control. Deep neural networks have shown remarkable success in grasp synthesis by learning rich and abstract representations of objects. When deployed at the edge, these models can enable low-latency, low-power inference, making real-time grasping feasible in resource-constrained environments. This work implements Hea…

Deep Neural Network Driven Simulation Based Inference Method for Pole Position Estimation under Model Misspecification
Daniel Sadasivan, Isaac Cordero, Andrew Graham, Cecilia Marsh, Daniel Kupcho, Melana Mourad, Maxim Mai
https://arxiv.org/abs/2507.18824

Deep Neural Network Driven Simulation Based Inference Method for Pole Position Estimation under Model Misspecification
Simulation Based Inference (SBI) is shown to yield more accurate resonance parameter estimates than traditional chi-squared minimization in certain cases of model misspecification, demonstrated through a case study of pi-pi scattering and the rho(770) resonance. Models fit to some data sets using chi-squared minimization can predict inaccurate pole positions for the rho(770), while SBI provides more robust predictions across the same models and data. This result is significant both as a proof o…

Deep Active Learning for Lung Disease Severity Classification from Chest X-rays: Learning with Less Data in the Presence of Class Imbalance
Roy M. Gabriel, Mohammadreza Zandehshahvar, Marly van Assen, Nattakorn Kittisut, Kyle Peters, Carlo N. De Cecco, Ali Adibi
https://arxiv.org/abs/2508.21263

Deep Active Learning for Lung Disease Severity Classification from Chest X-rays: Learning with Less Data in the Presence of Class Imbalance
To reduce the amount of required labeled data for lung disease severity classification from chest X-rays (CXRs) under class imbalance, this study applied deep active learning with a Bayesian Neural Network (BNN) approximation and weighted loss function. This retrospective study collected 2,319 CXRs from 963 patients (mean age, 59.2 $\pm$ 16.6 years; 481 female) at Emory Healthcare affiliated hospitals between January and November 2020. All patients had clinically confirmed COVID-19. Each CXR wa…

Hebbian Memory-Augmented Recurrent Networks: Engram Neurons in Deep Learning
Daniel Szelogowski
https://arxiv.org/abs/2507.21474 https://arxiv.org/pdf/2507…

Hebbian Memory-Augmented Recurrent Networks: Engram Neurons in Deep Learning
Despite success across diverse tasks, current artificial recurrent network architectures rely primarily on implicit hidden-state memories, limiting their interpretability and ability to model long-range dependencies. In contrast, biological neural systems employ explicit, associative memory traces (i.e., engrams) strengthened through Hebbian synaptic plasticity and activated sparsely during recall. Motivated by these neurobiological insights, we introduce the Engram Neural Network (ENN), a nove…

Multi-Utterance Speech Separation and Association Trained on Short Segments
Yuzhu Wang, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen
https://arxiv.org/abs/2507.02562

Multi-Utterance Speech Separation and Association Trained on Short Segments
Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing significantly longer recordings with multiple utterances per speaker than seen during training. In this paper, we investigate how existing approaches perform in this challenging scenario and propose a frequency-temporal recurrent neural network (FTRNN) that effective…

Aperiodic-sampled neural network controllers with closed-loop stability verifications (extended version)
Renjie Ma, Zhijian Hu, Rongni Yang, Ligang Wu
https://arxiv.org/abs/2506.18386

Aperiodic-sampled neural network controllers with closed-loop stability verifications (extended version)
In this paper, we synthesize two aperiodic-sampled deep neural network (DNN) control schemes, based on the closed-loop tracking stability guarantees. By means of the integral quadratic constraint coping with the input-output behaviour of system uncertainties/nonlinearities and the convex relaxations of nonlinear DNN activations leveraging their local sector-bounded attributes, we establish conditions to design the event- and self-triggered logics and to compute the ellipsoidal inner approximati…

VidFuncta: Towards Generalizable Neural Representations for Ultrasound Videos
Julia Wolleb, Florentin Bieder, Paul Friedrich, Hemant D. Tagare, Xenophon Papademetris
https://arxiv.org/abs/2507.21863

VidFuncta: Towards Generalizable Neural Representations for Ultrasound Videos
Ultrasound is widely used in clinical care, yet standard deep learning methods often struggle with full video analysis due to non-standardized acquisition and operator bias. We offer a new perspective on ultrasound video analysis through implicit neural representations (INRs). We build on Functa, an INR framework in which each image is represented by a modulation vector that conditions a shared neural network. However, its extension to the temporal domain of medical videos remains unexplored. T…

Graph neural networks for residential location choice: connection to classical logit models
Zhanhong Cheng, Lingqian Hu, Yuheng Bu, Yuqi Zhou, Shenhao Wang
https://arxiv.org/abs/2507.21334

Graph neural networks for residential location choice: connection to classical logit models
Researchers have adopted deep learning for classical discrete choice analysis as it can capture complex feature relationships and achieve higher predictive performance. However, the existing deep learning approaches cannot explicitly capture the relationship among choice alternatives, which has been a long-lasting focus in classical discrete choice models. To address the gap, this paper introduces Graph Neural Network (GNN) as a novel framework to analyze residential location choice. The GNN-ba…

Improving Liver Disease Diagnosis with SNNDeep: A Custom Spiking Neural Network Using Diverse Learning Algorithms
Zofia Rudnicka, Janusz Szczepanski, Agnieszka Pregowska
https://arxiv.org/abs/2508.20125

Improving Liver Disease Diagnosis with SNNDeep: A Custom Spiking Neural Network Using Diverse Learning Algorithms
Purpose: Spiking neural networks (SNNs) have recently gained attention as energy-efficient, biologically plausible alternatives to conventional deep learning models. Their application in high-stakes biomedical imaging remains almost entirely unexplored. Methods: This study introduces SNNDeep, the first tailored SNN specifically optimized for binary classification of liver health status from computed tomography (CT) features. To ensure clinical relevance and broad generalizability, the model was…

Onboard Hyperspectral Super-Resolution with Deep Pushbroom Neural Network
Davide Piccinini, Diego Valsesia, Enrico Magli
https://arxiv.org/abs/2507.20765 https://

Onboard Hyperspectral Super-Resolution with Deep Pushbroom Neural Network
Hyperspectral imagers on satellites obtain the fine spectral signatures essential for distinguishing one material from another at the expense of limited spatial resolution. Enhancing the latter is thus a desirable preprocessing step in order to further improve the detection capabilities offered by hyperspectral images on downstream tasks. At the same time, there is a growing interest towards deploying inference methods directly onboard of satellites, which calls for lightweight image super-reso…

Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
Yuan Yao, Jin Song, Jian Jin
https://arxiv.org/abs/2507.11137

Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
As valuable digital assets, deep neural networks necessitate robust ownership protection, positioning neural network watermarking (NNW) as a promising solution. Among various NNW approaches, weight-based methods are favored for their simplicity and practicality; however, they remain vulnerable to forging and overwriting attacks. To address those challenges, we propose NeuralMark, a robust method built around a hashed watermark filter. Specifically, we utilize a hash function to generate an irre…

Low-Complexity Neural Wind Noise Reduction for Audio Recordings
Hesam Eftekhari, Srikanth Raj Chetupalli, Shrishti Saha Shetu, Emanu\"el A. P. Habets, Oliver Thiergart
https://arxiv.org/abs/2507.01821

Low-Complexity Neural Wind Noise Reduction for Audio Recordings
Wind noise significantly degrades the quality of outdoor audio recordings, yet remains difficult to suppress in real-time on resource-constrained devices. In this work, we propose a low-complexity single-channel deep neural network that leverages the spectral characteristics of wind noise. Experimental results show that our method achieves performance comparable to the state-of-the-art low-complexity ULCNet model. The proposed model, with only 249K parameters and roughly 73 MHz of computational…

Simulating Posterior Bayesian Neural Networks with Dependent Weights
Nicola Apollonio, Giovanni Franzina, Giovanni Luca Torrisi
https://arxiv.org/abs/2507.22095 https://

Simulating Posterior Bayesian Neural Networks with Dependent Weights
In this paper we consider posterior Bayesian fully connected and feedforward deep neural networks with dependent weights. Particularly, if the likelihood is Gaussian, we identify the distribution of the wide width limit and provide an algorithm to sample from the network. In the shallow case we explicitly compute the distribution of the output, proving that it is a Gaussian mixture. All the theoretical results are numerically validated.

Mini-Batch Robustness Verification of Deep Neural Networks
Saar Tzour-Shaday, Dana Drachsler Cohen
https://arxiv.org/abs/2508.15454 https://arxiv.org/pdf/2…

Mini-Batch Robustness Verification of Deep Neural Networks
Neural network image classifiers are ubiquitous in many safety-critical applications. However, they are susceptible to adversarial attacks. To understand their robustness to attacks, many local robustness verifiers have been proposed to analyze $ε$-balls of inputs. Yet, existing verifiers introduce a long analysis time or lose too much precision, making them less effective for a large set of inputs. In this work, we propose a new approach to local robustness: group local robustness verificatio…

PatchDSU: Uncertainty Modeling for Out of Distribution Generalization in Keyword Spotting
Bronya Roni Chernyak, Yael Segal, Yosi Shrem, Joseph Keshet
https://arxiv.org/abs/2508.03190

PatchDSU: Uncertainty Modeling for Out of Distribution Generalization in Keyword Spotting
Deep learning models excel at many tasks but rely on the assumption that training and test data follow the same distribution. This assumption often does not hold in real-world speech systems, where distribution shifts are common due to varying environments, recording conditions, and speaker diversity. The method of Domain Shifts with Uncertainty (DSU) augments the input of each neural network layer based on the input feature statistics. It addresses the problem of out-of-domain generalization…

A Deep Convolutional Neural Network-Based Novel Class Balancing for Imbalance Data Segmentation
Atifa Kalsoom, M. A. Iftikhar, Amjad Ali, Zubair Shah, Shidin Balakrishnan, Hazrat Ali
https://arxiv.org/abs/2506.18474

A Deep Convolutional Neural Network-Based Novel Class Balancing for Imbalance Data Segmentation
Retinal fundus images provide valuable insights into the human eye's interior structure and crucial features, such as blood vessels, optic disk, macula, and fovea. However, accurate segmentation of retinal blood vessels can be challenging due to imbalanced data distribution and varying vessel thickness. In this paper, we propose BLCB-CNN, a novel pipeline based on deep learning and bi-level class balancing scheme to achieve vessel segmentation in retinal fundus images. The BLCB-CNN scheme uses …

Error analysis for the deep Kolmogorov method
Iulian C\^impean, Thang Do, Lukas Gonon, Arnulf Jentzen, Ionel Popescu
https://arxiv.org/abs/2508.17167 https://

Error analysis for the deep Kolmogorov method
The deep Kolmogorov method is a simple and popular deep learning based method for approximating solutions of partial differential equations (PDEs) of the Kolmogorov type. In this work we provide an error analysis for the deep Kolmogorov method for heat PDEs. Specifically, we reveal convergence with convergence rates for the overall mean square distance between the exact solution of the heat PDE and the realization function of the approximating deep neural network (DNN) associated with a stochas…

Near-optimal estimates for the $\ell^p$-Lipschitz constants of deep random ReLU neural networks
Sjoerd Dirksen, Patrick Finke, Paul Geuchen, Dominik St\"oger, Felix Voigtlaender
https://arxiv.org/abs/2506.19695

Near-optimal estimates for the $\ell^p$-Lipschitz constants of deep random ReLU neural networks
This paper studies the $\ell^p$-Lipschitz constants of ReLU neural networks $Φ: \mathbb{R}^d \to \mathbb{R}$ with random parameters for $p \in [1,\infty]$. The distribution of the weights follows a variant of the He initialization and the biases are drawn from symmetric distributions. We derive high probability upper and lower bounds for wide networks that differ at most by a factor that is logarithmic in the network's width and linear in its depth. In the special case of shallow networks, we …

TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction
St\'ephane d'Ascoli, J\'er\'emy Rapin, Yohann Benchetrit, Hubert Banville, Jean-R\'emi King
https://arxiv.org/abs/2507.22229

TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction
Historically, neuroscience has progressed by fragmenting into specialized domains, each focusing on isolated modalities, tasks, or brain regions. While fruitful, this approach hinders the development of a unified model of cognition. Here, we introduce TRIBE, the first deep neural network trained to predict brain responses to stimuli across multiple modalities, cortical areas and individuals. By combining the pretrained representations of text, audio and video foundational models and handling th…

Deep Uzawa for Kinetic Transport with Lagrange-Enforced Boundaries
Charalambos Makridakis, Aaron Pim, Tristan Pryer, Nikolaos Rekatsinas
https://arxiv.org/abs/2507.19907 https:/…

Deep Uzawa for Kinetic Transport with Lagrange-Enforced Boundaries
We propose a neural network framework for solving stationary linear transport equations with inflow boundary conditions. The method represents the solution using a neural network and imposes the boundary condition via a Lagrange multiplier, based on a saddle-point formulation inspired by the classical Uzawa algorithm. The scheme is mesh-free, compatible with automatic differentiation and extends naturally to problems with scattering and heterogeneous media. We establish convergence of the conti…

Smart Video Capsule Endoscopy: Raw Image-Based Localization for Enhanced GI Tract Investigation
Oliver Bause, Julia Werner, Paul Palomero Bernardo, Oliver Bringmann
https://arxiv.org/abs/2507.23398

Smart Video Capsule Endoscopy: Raw Image-Based Localization for Enhanced GI Tract Investigation
For many real-world applications involving low-power sensor edge devices deep neural networks used for image classification might not be suitable. This is due to their typically large model size and require- ment of operations often exceeding the capabilities of such resource lim- ited devices. Furthermore, camera sensors usually capture images with a Bayer color filter applied, which are subsequently converted to RGB images that are commonly used for neural network training. However, on resour…

Polynomial Chaos Expansion for Operator Learning
Himanshu Sharma, Luk\'a\v{s} Nov\'ak, Michael D. Shields
https://arxiv.org/abs/2508.20886 https://…

Polynomial Chaos Expansion for Operator Learning
Operator learning (OL) has emerged as a powerful tool in scientific machine learning (SciML) for approximating mappings between infinite-dimensional functional spaces. One of its main applications is learning the solution operator of partial differential equations (PDEs). While much of the progress in this area has been driven by deep neural network-based approaches such as Deep Operator Networks (DeepONet) and Fourier Neural Operator (FNO), recent work has begun to explore traditional machine …

Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problems
Yutong Du, Zicheng Liu, Bazargul Matkerim, Changyou Li, Yali Zong, Bo Qi, Jingwei Kou
https://arxiv.org/abs/2507.16321

Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problems
In recent years, deep learning-based methods have been proposed for solving inverse scattering problems (ISPs), but most of them heavily rely on data and suffer from limited generalization capabilities. In this paper, a new solving scheme is proposed where the solution is iteratively updated following the updating of the physics-driven neural network (PDNN), the hyperparameters of which are optimized by minimizing the loss function which incorporates the constraints from the collected scattered…

Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
Saman Yazdannik, Morteza Tayefi, Shamim Sanisales
https://arxiv.org/abs/2508.14536 https://arxiv.or…

Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
The performance of Deep Q-Networks (DQN) is critically dependent on the ability of its underlying neural network to accurately approximate the action-value function. Standard function approximators, such as multi-layer perceptrons, may struggle to efficiently represent the complex value landscapes inherent in many reinforcement learning problems. This paper introduces a novel architecture, the Chebyshev-DQN (Ch-DQN), which integrates a Chebyshev polynomial basis into the DQN framework to create…

Optimal Convergence Rates of Deep Neural Network Classifiers
Zihan Zhang, Lei Shi, Ding-Xuan Zhou
https://arxiv.org/abs/2506.14899 https://

Optimal Convergence Rates of Deep Neural Network Classifiers
In this paper, we study the binary classification problem on $[0,1]^d$ under the Tsybakov noise condition (with exponent $s \in [0,\infty]$) and the compositional assumption. This assumption requires the conditional class probability function of the data distribution to be the composition of $q+1$ vector-valued multivariate functions, where each component function is either a maximum value function or a Hölder-$β$ smooth function that depends only on $d_*$ of its input variables. Notably, $d_…