Tootfinder

Distributionally robust approximation property of neural networks
Mihriban Ceylan, David J. Pr\"omel
https://arxiv.org/abs/2510.09177 https://arxiv.or…

Distributionally robust approximation property of neural networks
The universal approximation property uniformly with respect to weakly compact families of measures is established for several classes of neural networks. To that end, we prove that these neural networks are dense in Orlicz spaces, thereby extending classical universal approximation theorems even beyond the traditional $L^p$-setting. The covered classes of neural networks include widely used architectures like feedforward neural networks with non-polynomial activation functions, deep narrow netw…

Agentic Graph Neural Networks for Wireless Communications and Networking Towards Edge General Intelligence: A Survey
Yang Lu, Shengli Zhang, Chang Liu, Ruichen Zhang, Bo Ai, Dusit Niyato, Wei Ni, Xianbin Wang, Abbas Jamalipour
https://arxiv.org/abs/2508.08620

Agentic Graph Neural Networks for Wireless Communications and Networking Towards Edge General Intelligence: A Survey
The rapid advancement of communication technologies has driven the evolution of communication networks towards both high-dimensional resource utilization and multifunctional integration. This evolving complexity poses significant challenges in designing communication networks to satisfy the growing quality-of-service and time sensitivity of mobile applications in dynamic environments. Graph neural networks (GNNs) have emerged as fundamental deep learning (DL) models for complex communication ne…

The Enduring Dominance of Deep Neural Networks: A Critical Analysis of the Fundamental Limitations of Quantum Machine Learning and Spiking Neural Networks
Takehiro Ishikawa
https://arxiv.org/abs/2510.08591

The Enduring Dominance of Deep Neural Networks: A Critical Analysis of the Fundamental Limitations of Quantum Machine Learning and Spiking Neural Networks
Recent advancements in QML and SNNs have generated considerable excitement, promising exponential speedups and brain-like energy efficiency to revolutionize AI. However, this paper argues that they are unlikely to displace DNNs in the near term. QML struggles with adapting backpropagation due to unitary constraints, measurement-induced state collapse, barren plateaus, and high measurement overheads, exacerbated by the limitations of current noisy intermediate-scale quantum hardware, overfitting…

Outsmarting Linear Neural Networks via an Incoherent Light-Driven Optical Extreme Learner with Data Reverberation
Bofeng Liu, Xu Mei, Sadman Shafi, Tunan Xia, Iam-Choon Khoo, Zhiwen Liu, Xingjie Ni
https://arxiv.org/abs/2508.08428

Outsmarting Linear Neural Networks via an Incoherent Light-Driven Optical Extreme Learner with Data Reverberation
Artificial neural networks have revolutionized fields from computer vision to natural language processing, yet their growing energy and computational demands threaten future progress. Optical neural networks promise greater speed, bandwidth, and energy efficiency, but suffer from weak optical nonlinearities. Here, we demonstrate a low-power, incoherent-light-driven optical extreme learner that leverages 'data nonlinearity' from optical pattern reverberations, eliminating reliance on intrinsic n…

Augmented data and neural networks for robust epidemic forecasting: application to COVID-19 in Italy
Giacomo Dimarco, Federica Ferrarese, Lorenzo Pareschi
https://arxiv.org/abs/2510.09192

Augmented data and neural networks for robust epidemic forecasting: application to COVID-19 in Italy
In this work, we propose a data augmentation strategy aimed at improving the training phase of neural networks and, consequently, the accuracy of their predictions. Our approach relies on generating synthetic data through a suitable compartmental model combined with the incorporation of uncertainty. The available data are then used to calibrate the model, which is further integrated with deep learning techniques to produce additional synthetic data for training. The results show that neural net…

Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models
Yankun Han
https://arxiv.org/abs/2510.09423 https://arxiv.org…

Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models
Weight initialization governs signal propagation and gradient flow at the start of training. This paper offers a theory-grounded and empirically validated study across two regimes: compact ReLU multilayer perceptrons and GPT-2-style transformers. First, a logarithmic sweep of the initial standard deviation maps vanishing and exploding regimes and identifies a broad stability band with standard deviations between 1e-2 and 1e-1. Second, a controlled comparison shows that Kaiming (fan-in) initiali…

Optimised neural networks for online processing of ATLAS calorimeter data on FPGAs
Georges Aad, Raphael Bertrand, Lauri Laatu, Emmanuel Monnier, Arno Straessner, Nairit Sur, Johann C. Voigt
https://arxiv.org/abs/2510.11469

Optimised neural networks for online processing of ATLAS calorimeter data on FPGAs
A study of neural network architectures for the reconstruction of the energy deposited in the cells of the ATLAS liquid-argon calorimeters under high pile-up conditions expected at the HL-LHC is presented. These networks are designed to run on the FPGA-based readout hardware of the calorimeters under strict size and latency constraints. Several architectures, including Dense, Recurrent (RNN), and Convolutional (CNN) neural networks, are optimised using a Bayesian procedure that balances energy …

Adaptive Decoding via Hierarchical Neural Information Gradients in Mouse Visual Tasks
Jingyi Feng, Xiang Feng
https://arxiv.org/abs/2510.09451 https://arxi…

Adaptive Decoding via Hierarchical Neural Information Gradients in Mouse Visual Tasks
Understanding the encoding and decoding mechanisms of dynamic neural responses to different visual stimuli is an important topic in exploring how the brain represents visual information. Currently, hierarchically deep neural networks (DNNs) have played a significant role as tools for mining the core features of complex data. However, most methods often overlook the dynamic generation process of neural data, such as hierarchical brain's visual data, within the brain's structure. In the decoding …

The $\alpha$-Cap Process: A Continuous Model for Random Geometric Networks of Binary Neurons
Mirabel Reid, Daniel J. Zhang
https://arxiv.org/abs/2508.09396 https://

The $α$-Cap Process: A Continuous Model for Random Geometric Networks of Binary Neurons
Recurrent networks of binary neurons are a foundational concept in artificial intelligence. While these networks are traditionally assumed to be fully connected, complex dynamics can emerge when the graph structure is varied. One graph structure of particular interest is the geometric random graph, which models the spatial dependencies present in biological neural networks. In such classes of graphs, global state dependencies tend to complicate analysis, motivating the study of their dynamics i…

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
Ridiculogram:

Graph Neural Network-Based Multicast Routing for On-Demand Streaming Services in 6G Networks
Xiucheng Wang, Zien Wang, Nan Cheng, Wenchao Xu, Wei Quan, Xuemin Shen
https://arxiv.org/abs/2510.11109

Graph Neural Network-Based Multicast Routing for On-Demand Streaming Services in 6G Networks
The increase of bandwidth-intensive applications in sixth-generation (6G) wireless networks, such as real-time volumetric streaming and multi-sensory extended reality, demands intelligent multicast routing solutions capable of delivering differentiated quality-of-service (QoS) at scale. Traditional shortest-path and multicast routing algorithms are either computationally prohibitive or structurally rigid, and they often fail to support heterogeneous user demands, leading to suboptimal resource …

Evolution of linear matter perturbations with error-bounded bundle physics-informed neural networks
Luca Gomez Bachar, Augusto T. Chantada, Susana J. Landau, Claudia G. Sc\'occola, Pavlos Protopapas
https://arxiv.org/abs/2508.08443

Evolution of linear matter perturbations with error-bounded bundle physics-informed neural networks
We consider the evolution of linear matter perturbations in the context of the standard cosmological model ($Λ$CDM) and a phenomenological modified gravity model. We use the physics-informed neural network (PINN) bundle method, which allows to integrate differential systems as an alternative to the traditional numerical method. We apply the PINN bundle method to the equation that describes the matter perturbation evolution, to compare its outcomes with recent data on structure growth, $fσ_8$.…

Accelerated prediction of dielectric functions in solar cell materials with graph neural networks
Caden Ginter, Kamal Choudhary, Subhasish Mandal
https://arxiv.org/abs/2510.08738

Accelerated prediction of dielectric functions in solar cell materials with graph neural networks
We present an atomistic line graph neural network (ALIGNN) model for predicting dielectric functions directly from crystal structures. Trained on $\sim$7000 dielectric functions from the JARVIS-DFT database computed with a meta-GGA exchange-correlation functional, the model accurately reproduces spectral features, including peak intensities and overall line shapes, while enabling efficient high-throughput screening. Applied to the recently developed Alexandria materials database, containing ove…

Stochastic Decentralized Optimization of Non-Smooth Convex and Convex-Concave Problems over Time-Varying Networks
Maxim Divilkovskiy, Alexander Gasnikov
https://arxiv.org/abs/2508.09029

Stochastic Decentralized Optimization of Non-Smooth Convex and Convex-Concave Problems over Time-Varying Networks
We study non-smooth stochastic decentralized optimization problems over time-varying networks, where objective functions are distributed across nodes and network connections may intermittently appear or break. Specifically, we consider two settings: (i) stochastic non-smooth (strongly) convex optimization, and (ii) stochastic non-smooth (strongly) convex-(strongly) concave saddle point optimization. Convex problems of this type commonly arise in deep neural network training, while saddle point …

VM-UNSSOR: Unsupervised Neural Speech Separation Enhanced by Higher-SNR Virtual Microphone Arrays
Shulin He, Zhong-Qiu Wang
https://arxiv.org/abs/2510.08914 https://

VM-UNSSOR: Unsupervised Neural Speech Separation Enhanced by Higher-SNR Virtual Microphone Arrays
Blind speech separation (BSS) aims to recover multiple speech sources from multi-channel, multi-speaker mixtures under unknown array geometry and room impulse responses. In unsupervised setup where clean target speech is not available for model training, UNSSOR proposes a mixture consistency (MC) loss for training deep neural networks (DNN) on over-determined training mixtures to realize unsupervised speech separation. However, when the number of microphones of the training mixtures decreases, …

Bio-Inspired Artificial Neural Networks based on Predictive Coding
Davide Casnici, Charlotte Frenkel, Justin Dauwels
https://arxiv.org/abs/2508.08762 https://

Bio-Inspired Artificial Neural Networks based on Predictive Coding
Backpropagation (BP) of errors is the backbone training algorithm for artificial neural networks (ANNs). It updates network weights through gradient descent to minimize a loss function representing the mismatch between predictions and desired outputs. BP uses the chain rule to propagate the loss gradient backward through the network hierarchy, allowing efficient weight updates. However, this process requires weight updates at every layer to rely on a global error signal generated at the network…

Whither symbols in the era of advanced neural networks?
Thomas L. Griffiths, Brenden M. Lake, R. Thomas McCoy, Ellie Pavlick, Taylor W. Webb
https://arxiv.org/abs/2508.05776 htt…

Whither symbols in the era of advanced neural networks?
Some of the strongest evidence that human minds should be thought about in terms of symbolic systems has been the way they combine ideas, produce novelty, and learn quickly. We argue that modern neural networks -- and the artificial intelligence systems built upon them -- exhibit similar abilities. This undermines the argument that the cognitive processes and representations used by human minds are symbolic, although the fact that these neural networks are typically trained on data generated by…

Intelligent backpropagated neural networks application on Couette-Poiseuille flow of variable viscosity in a composite porous channel filled with an anisotropic porous layer
Timir Karmakar, Amrita Mandal
https://arxiv.org/abs/2510.08745

Intelligent backpropagated neural networks application on Couette-Poiseuille flow of variable viscosity in a composite porous channel filled with an anisotropic porous layer
This study examines Couette-Poiseuille flow of variable viscosity within a channel that is partially filled with a porous medium. To enhance its practical relevance, we assume that the porous medium is anisotropic with permeability varying in all directions, making it a positive semidefinite matrix in the momentum equation. We assume the Navier-Stokes equations govern the flow in the free flow region, while the Brinkman-Forchheimer-extended Darcy's equation governs the flow inside the porous me…

Identification of molecular line emission using Convolutional Neural Networks
Nina Kessler, Timea Csengeri, David Cornu, Sylvain Bontemps, Laure Bouscasse
https://arxiv.org/abs/2510.09119

Identification of molecular line emission using Convolutional Neural Networks
Complex organic molecules (COMs) are observed to be abundant in various astrophysical environments, in particular toward star forming regions they are observed both toward protostellar envelopes as well as shocked regions. Emission spectrum especially of heavier COMs may consists of up to hundreds of lines, where line blending hinders the analysis. However, identifying the molecular composition of the gas leading to the observed millimeter spectra is the first step toward a quantitative analysi…

CryptGNN: Enabling Secure Inference for Graph Neural Networks
Pritam Sen, Yao Ma, Cristian Borcea
https://arxiv.org/abs/2509.09107 https://arxiv.org/pdf/25…

CryptGNN: Enabling Secure Inference for Graph Neural Networks
We present CryptGNN, a secure and effective inference solution for third-party graph neural network (GNN) models in the cloud, which are accessed by clients as ML as a service (MLaaS). The main novelty of CryptGNN is its secure message passing and feature transformation layers using distributed secure multi-party computation (SMPC) techniques. CryptGNN protects the client's input data and graph structure from the cloud provider and the third-party model owner, and it protects the model paramete…

Estimating classical mutual information between quantum subsystems with neural networks
D. A. Konyshev, V. V. Mazurenko
https://arxiv.org/abs/2508.07652 https://

Estimating classical mutual information between quantum subsystems with neural networks
Characterizing correlations in a quantum system on the basis of the results of the projective measurements can be performed with different means including the calculation of the classical mutual information. Generally, estimating such information-entropy-based quantities requires having complete statistics of the system's states. Here we explore the possibility to reconstruct the classical mutual information and specific entropy of a quantum system with neural network approach on the basis of l…

UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale
Yuhao Wang, Wei Xi
https://arxiv.org/abs/2508.09000

UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale
Convolutional neural networks (ConvNets) with large effective receptive field (ERF), still in their early stages, have demonstrated promising effectiveness while constrained by high parameters and FLOPs costs and disrupted asymptotically Gaussian distribution (AGD) of ERF. This paper proposes an alternative paradigm: rather than merely employing extremely large ERF, it is more effective and efficient to expand the ERF while maintaining AGD of ERF by proper combination of smaller kernels, such a…

Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations
Ryo Aihara, Yoshiki Masuyama, Gordon Wichern, Fran\c{c}ois G. Germain, Jonathan Le Roux
https://arxiv.org/abs/2508.08399

Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations
Neural audio codecs (NACs), which use neural networks to generate compact audio representations, have garnered interest for their applicability to many downstream tasks -- especially quantized codecs due to their compatibility with large language models. However, unlike text, speech conveys not only linguistic content but also rich paralinguistic features. Encoding these elements in an entangled fashion may be suboptimal, as it limits flexibility. For instance, voice conversion (VC) aims to con…

SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
Qihu Xie, Yuan Li, Yi Kang
https://arxiv.org/abs/2509.07373 https…

SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
Implicit neural representations have recently been extended to represent convolutional neural network weights via neural representation for neural networks, offering promising parameter compression benefits. However, standard multi-layer perceptrons used in neural representation for neural networks exhibit a pronounced spectral bias, hampering their ability to reconstruct high-frequency details effectively. In this paper, we propose SBS, a parameter-efficient enhancement to neural representatio…

Neural Beam Field for Spatial Beam RSRP Prediction
Keqiang Guo, Yuheng Zhong, Xin Tong, Jiangbin Lyu, Rui Zhang
https://arxiv.org/abs/2508.06956 https://ar…

Neural Beam Field for Spatial Beam RSRP Prediction
Accurately predicting beam-level reference signal received power (RSRP) is essential for beam management in dense multi-user wireless networks, yet challenging due to high measurement overhead and fast channel variations. This paper proposes Neural Beam Field (NBF), a hybrid neural-physical framework for efficient and interpretable spatial beam RSRP prediction. Central to our approach is the introduction of the Multi-path Conditional Power Profile (MCPP), which bridges site-specific multipath p…

Augmenting Neural Networks-based Model Approximators in Robotic Force-tracking Tasks
Kevin Saad, Vincenzo Petrone, Enrico Ferrentino, Pasquale Chiacchio, Francesco Braghin, Loris Roveda
https://arxiv.org/abs/2509.08440

Augmenting Neural Networks-based Model Approximators in Robotic Force-tracking Tasks
As robotics gains popularity, interaction control becomes crucial for ensuring force tracking in manipulator-based tasks. Typically, traditional interaction controllers either require extensive tuning, or demand expert knowledge of the environment, which is often impractical in real-world applications. This work proposes a novel control strategy leveraging Neural Networks (NNs) to enhance the force-tracking behavior of a Direct Force Controller (DFC). Unlike similar previous approaches, it acco…

Replaced article(s) found for cs.LO. https://arxiv.org/list/cs.LO/new
[1/1]:
- Verifying Quantized Graph Neural Networks is PSPACE-complete
Marco S\"alzer, Fran\c{c}ois Schwarzentruber, Nicolas Troquard

A mathematical theory for understanding when abstract representations emerge in neural networks
Bin Wang, W. Jeffrey Johnston, Stefano Fusi
https://arxiv.org/abs/2510.09816 http…

A mathematical theory for understanding when abstract representations emerge in neural networks
Recent experiments reveal that task-relevant variables are often encoded in approximately orthogonal subspaces of the neural activity space. These disentangled low-dimensional representations are observed in multiple brain areas and across different species, and are typically the result of a process of abstraction that supports simple forms of out-of-distribution generalization. The mechanisms by which such geometries emerge remain poorly understood, and the mechanisms that have been investigat…

WarpPINN-fibers: improved cardiac strain estimation from cine-MR with physics-informed neural networks
Felipe \'Alvarez Barrientos, Tom\'as Banduc, Isabeau Sirven, Francisco Sahli Costabal
https://arxiv.org/abs/2509.08872

WarpPINN-fibers: improved cardiac strain estimation from cine-MR with physics-informed neural networks
The contractile motion of the heart is strongly determined by the distribution of the fibers that constitute cardiac tissue. Strain analysis informed with the orientation of fibers allows to describe several pathologies that are typically associated with impaired mechanics of the myocardium, such as cardiovascular disease. Several methods have been developed to estimate strain-derived metrics from traditional imaging techniques. However, the physical models underlying these methods do not inclu…

A Spin Glass Characterization of Neural Networks
Jun Li
https://arxiv.org/abs/2508.07397 https://arxiv.org/pdf/2508.07397

A Spin Glass Characterization of Neural Networks
This work presents a statistical mechanics characterization of neural networks, motivated by the replica symmetry breaking (RSB) phenomenon in spin glasses. A Hopfield-type spin glass model is constructed from a given feedforward neural network (FNN). Overlaps between simulated replica samples serve as a characteristic descriptor of the FNN. The connection between the spin-glass description and commonly studied properties of the FNN -- such as data fitting, capacity, generalization, and robustn…

CKFNet: Neural Network Aided Cubature Kalman filtering
Jinhui Hu, Haiquan Zhao, Yi Peng
https://arxiv.org/abs/2508.09727 https://arxiv.org/pdf/2508.09727…

CKFNet: Neural Network Aided Cubature Kalman filtering
The cubature Kalman filter (CKF), while theoretically rigorous for nonlinear estimation, often suffers performance degradation due to model-environment mismatches in practice. To address this limitation, we propose CKFNet-a hybrid architecture that synergistically integrates recurrent neural networks (RNN) with the CKF framework while preserving its cubature principles. Unlike conventional model-driven approaches, CKFNet embeds RNN modules in the prediction phase to dynamically adapt to unmodel…

Integrating Structure-Aware Attention and Knowledge Graphs in Explainable Recommendation Systems
Shuangquan Lyu, Ming Wang, Huajun Zhang, Jiasen Zheng, Junjiang Lin, Xiaoxuan Sun
https://arxiv.org/abs/2510.10109

Integrating Structure-Aware Attention and Knowledge Graphs in Explainable Recommendation Systems
This paper designs and implements an explainable recommendation model that integrates knowledge graphs with structure-aware attention mechanisms. The model is built on graph neural networks and incorporates a multi-hop neighbor aggregation strategy. By integrating the structural information of knowledge graphs and dynamically assigning importance to different neighbors through an attention mechanism, the model enhances its ability to capture implicit preference relationships. In the proposed me…

A Morphology-Adaptive Random Feature Method for Inverse Source Problem of the Helmholtz Equation
Xinwei Hu, Jingrun Chen, Haijun Yu
https://arxiv.org/abs/2510.09213 https://

A Morphology-Adaptive Random Feature Method for Inverse Source Problem of the Helmholtz Equation
The inverse source problem for the Helmholtz equation poses significant challenges, particularly when sources exhibit complex or discontinuous geometries. Traditional numerical methods suffer from prohibitive computational costs, while machine learning-based approaches such as Physics-Informed Neural Networks (PINNs) and the Random Feature Method (RFM) -- though computationally efficient for inverse problems -- lack the intrinsic machinery to handle the sharp morphological features in such sing…

Low-cost Pyranometer-Based ANN Approach for MPPT in Solar PV Systems
Luiz Fernando M. Arruda, Moises Ferber, Diego Greff
https://arxiv.org/abs/2510.10313 https://

Low-cost Pyranometer-Based ANN Approach for MPPT in Solar PV Systems
This article presents a study on the application of artificial neural networks (ANNs) for maximum power point tracking (MPPT) in photovoltaic (PV) systems using low-cost pyranometer sensors. The proposed approach integrates pyranometers, temperature sensors, and an ANN to estimate the duty cycle of a DC/DC converter, enabling the system to consistently operate at its maximum power point. The strategy was implemented in the local control of a Cuk converter and experimentally validated against th…

Replaced article(s) found for cs.CC. https://arxiv.org/list/cs.CC/new
[1/1]:
- Verifying Quantized Graph Neural Networks is PSPACE-complete
Marco S\"alzer, Fran\c{c}ois Schwarzentruber, Nicolas Troquard

Toric geometry of ReLU neural networks
Yaoying Fu
https://arxiv.org/abs/2509.05894 https://arxiv.org/pdf/2509.05894…

Toric geometry of ReLU neural networks
Given a continuous finitely piecewise linear function $f:\mathbb{R}^{n_0} \to \mathbb{R}$ and a fixed architecture $(n_0,\ldots,n_k;1)$ of feedforward ReLU neural networks, the exact function realization problem is to determine when some network with the given architecture realizes $f$. To develop a systematic way to answer these questions, we establish a connection between toric geometry and ReLU neural networks. This approach enables us to utilize numerous structures and tools from algebraic …

From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
Peyman Baghershahi, Gregoire Fournier, Pranav Nyati, Sourav Medya
https://arxiv.org/abs/2508.07117

From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs, which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are not inherently interpretable and thus, many explanation methods have been proposed. However, existing explanation methods often struggle to generate interpretable, fine-grained rationales, especially when node attributes include rich natural language. In this work, …

Architecture Induces Structural Invariant Manifolds of Neural Network Training Dynamics
Jiajie Zhao, Tao Luo, Yaoyu Zhang
https://arxiv.org/abs/2510.09564 https://

Architecture Induces Structural Invariant Manifolds of Neural Network Training Dynamics
While architecture is recognized as key to the performance of deep neural networks, its precise effect on training dynamics has been unclear due to the confounding influence of data and loss functions. This paper proposed an analytic framework based on the geometric control theory to characterize the dynamical properties intrinsic to a model's parameterization. We prove that the Structural Invariant Manifolds (SIMs) of an analytic model $F(\mathbfθ)(\mathbf{x})$--submanifolds that confine grad…

Deep Learning of the Biswas-Chatterjee-Sen Model
J. F. Silva Neto, D. S. M. Alencar, L. T. Brito, G. A. Alves, F. W. S. Lima, A. Macedo-Filho, R. S. Ferreira, T. F. A. Alves
https://arxiv.org/abs/2510.09446

Deep Learning of the Biswas-Chatterjee-Sen Model
We investigate the critical properties of kinetic continuous opinion dynamics using deep learning techniques. The system consists of $N$ continuous spin variables in the interval $[-1,1]$. Dense neural networks are trained on spin configuration data generated via kinetic Monte Carlo simulations, accurately identifying the critical point on both square and triangular lattices. Classical unsupervised learning with principal component analysis reproduces the magnetization and allows estimation of …

Replaced article(s) found for q-fin.TR. https://arxiv.org/list/q-fin.TR/new
[1/1]:
- Efficient Triangular Arbitrage Detection via Graph Neural Networks
Di Zhang

Geometry-Aware Spiking Graph Neural Network
Bowen Zhang, Genan Dai, Hu Huang, Long Lan
https://arxiv.org/abs/2508.06793 https://arxiv.org/pdf/2508.06793

Geometry-Aware Spiking Graph Neural Network
Graph Neural Networks (GNNs) have demonstrated impressive capabilities in modeling graph-structured data, while Spiking Neural Networks (SNNs) offer high energy efficiency through sparse, event-driven computation. However, existing spiking GNNs predominantly operate in Euclidean space and rely on fixed geometric assumptions, limiting their capacity to model complex graph structures such as hierarchies and cycles. To overcome these limitations, we propose \method{}, a novel Geometry-Aware Spikin…

Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
Anis Hamadouche, Haifeng Luo, Mathini Sellathurai, Tharm Ratnarajah
https://arxiv.org/abs/2508.08468

Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
This paper introduces a new AI-based Audio-Visual Speech Enhancement (AVSE) system and presents a comparative performance analysis of different deployment architectures. The proposed AVSE system employs convolutional neural networks (CNNs) for spectral feature extraction and long short-term memory (LSTM) networks for temporal modeling, enabling robust speech enhancement through multimodal fusion of audio and visual cues. Multiple deployment scenarios are investigated, including cloud-based, edg…

Biomedical Signal Processing: EEG and ECG Classification with Discrete Wavelet Transforms, Energy Distribution, and Convolutional Neural Networks
Justin London
https://arxiv.org/abs/2508.08602

Biomedical Signal Processing: EEG and ECG Classification with Discrete Wavelet Transforms, Energy Distribution, and Convolutional Neural Networks
Biomedical signal processing extract meaningful information from physiological signals like electrocardiograms (ECGs), electroencephalograms (EEGs), and electromyograms (EMGs) to diagnose, monitor, and treat medical conditions and diseases such as seizures, cardiomyopathy, and neuromuscular disorders, respectively. Traditional manual physician analysis of electrical recordings is prone to human error as subtle anomolies may not be detected. Recently, advanced deep learning has significantly imp…

Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning
Soumia Mehimeh
https://arxiv.org/abs/2508.09277 https://…

Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning
Value function initialization (VFI) is an effective way to achieve a jumpstart in reinforcement learning (RL) by leveraging value estimates from prior tasks. While this approach is well established in tabular settings, extending it to deep reinforcement learning (DRL) poses challenges due to the continuous nature of the state-action space, the noisy approximations of neural networks, and the impracticality of storing all past models for reuse. In this work, we address these challenges and intro…

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
Rid…

Solving Approximation Tasks with Greedy Deep Kernel Methods
Marian Klink, Tobias Ehring, Robin Herkert, Robin Lautenschlager, Dominik G\"oddeke, Bernard Haasdonk
https://arxiv.org/abs/2508.08759

Solving Approximation Tasks with Greedy Deep Kernel Methods
Kernel methods are versatile tools for function approximation and surrogate modeling. In particular, greedy techniques offer computational efficiency and reliability through inherent sparsity and provable convergence. Inspired by the success of deep neural networks and structured deep kernel networks, we consider deep, multilayer kernels for greedy approximation. This multilayer structure, consisting of linear kernel layers and optimizable kernel activation function layers in an alternating fas…

Explainable Ensemble Learning for Graph-Based Malware Detection
Hossein Shokouhinejad, Roozbeh Razavi-Far, Griffin Higgins, Ali A Ghorbani
https://arxiv.org/abs/2508.09801 https…

Explainable Ensemble Learning for Graph-Based Malware Detection
Malware detection in modern computing environments demands models that are not only accurate but also interpretable and robust to evasive techniques. Graph neural networks (GNNs) have shown promise in this domain by modeling rich structural dependencies in graph-based program representations such as control flow graphs (CFGs). However, single-model approaches may suffer from limited generalization and lack interpretability, especially in high-stakes security applications. In this paper, we prop…

Neural Networks for 3D Characterization of AGATA Crystals
Mojahed Abushawish, Guillaume Baulieu, J\'er\'emie Dudouet, Olivier St\'ezowski
https://arxiv.org/abs/2508.06545

Neural Networks for 3D Characterization of AGATA Crystals
Precise localization of gamma-ray interactions is crucial for the performance of AGATA. The Pulse Shape Analysis (PSA) method used for the position estimation relies on simulated signals database. The Pulse Shape Comparison Scanning (PSCS) method was used to scan AGATA crystals in order to produce an experimental database. This paper presents a novel approach using LSTM neural networks to determine the 3D interaction position of gamma rays within AGATA crystals, trained on data from the Strasbo…

Verifying Graph Neural Networks with Readout is Intractable
Artem Chernobrovkin, Marco S\"alzer, Fran\c{c}ois Schwarzentruber, Nicolas Troquard
https://arxiv.org/abs/2510.08045

Verifying Graph Neural Networks with Readout is Intractable
We introduce a logical language for reasoning about quantized aggregate-combine graph neural networks with global readout (ACR-GNNs). We provide a logical characterization and use it to prove that verification tasks for quantized GNNs with readout are (co)NEXPTIME-complete. This result implies that the verification of quantized GNNs is computationally intractable, prompting substantial research efforts toward ensuring the safety of GNN-based systems. We also experimentally demonstrate that quan…

Modeling Dynamic Gas-Liquid Interfaces in Underwater Explosions Using Interval-Constrained Physics-Informed Neural Networks
Fulin Xing, Junjie Li, Ze Tao, Fujun Liu, Yong Tan
https://arxiv.org/abs/2508.07633

Modeling Dynamic Gas-Liquid Interfaces in Underwater Explosions Using Interval-Constrained Physics-Informed Neural Networks
Underwater explosion modeling faces a critical challenge of simultaneously resolving shock waves and gas-liquid interfaces, as traditional methods struggle to balance accuracy and computational efficiency. To address this, we develop a physics-informed neural network (PINN) framework featuring a dual-network architecture, that one network learns flow-field variables (pressure, density, velocity) from simulation data, while another network tracks the gas-liquid interface despite lacking direct n…

Testing the Cosmic Distance Duality Relation with Neural Kernel Gaussian Process Regression
Xin Luo, Nan Liang
https://arxiv.org/abs/2508.07040 https://arx…

Testing the Cosmic Distance Duality Relation with Neural Kernel Gaussian Process Regression
In this work, we test the cosmic distance duality relation (CDDR) by combining Pantheon+ Type Ia supernova (SNe Ia) data and DESI DR2 baryon acoustic oscillation (BAO) measurements. To resolve the redshift mismatch between the two datasets, we develop a new method called Neural Kernel Gaussian Process Regression (NKGPR), which uses two neural networks to simultaneously learn the mean and kernel functions of a Gaussian process. This approach improves upon traditional Gaussian process regression …

Deep Learning to Identify the Spatio-Temporal Cascading Effects of Train Delays in a High-Density Network
Vu Duc Anh Nguyen, Ziyue Li
https://arxiv.org/abs/2510.09350 https://…

Deep Learning to Identify the Spatio-Temporal Cascading Effects of Train Delays in a High-Density Network
The operational efficiency of railway networks, a cornerstone of modern economies, is persistently undermined by the cascading effects of train delays. Accurately forecasting this delay propagation is a critical challenge for real-time traffic management. While recent research has leveraged Graph Neural Networks (GNNs) to model the network structure of railways, a significant gap remains in developing frameworks that provide multi-step autoregressive forecasts at a network-wide scale, while sim…

Forward-Forward Autoencoder Architectures for Energy-Efficient Wireless Communications
Daniel Seifert, Onur G\"unl\"u, Rafael F. Schaefer
https://arxiv.org/abs/2510.11418

Forward-Forward Autoencoder Architectures for Energy-Efficient Wireless Communications
The application of deep learning to the area of communications systems has been a growing field of interest in recent years. Forward-forward (FF) learning is an efficient alternative to the backpropagation (BP) algorithm, which is the typically used training procedure for neural networks. Among its several advantages, FF learning does not require the communication channel to be differentiable and does not rely on the global availability of partial derivatives, allowing for an energy-efficient i…

Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented Generation
Vibhor Agrawal, Fay Wang, Rishi Puri
https://arxiv.org/abs/2508.05647 https://

Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented Generation
We present a novel graph neural network (GNN) architecture for retrieval-augmented generation (RAG) that leverages query-aware attention mechanisms and learned scoring heads to improve retrieval accuracy on complex, multi-hop questions. Unlike traditional dense retrieval methods that treat documents as independent entities, our approach constructs per-episode knowledge graphs that capture both sequential and semantic relationships between text chunks. We introduce an Enhanced Graph Attention Ne…

Efficient classical computation of the neural tangent kernel of quantum neural networks
Anderson Melchor Hernandez, Davide Pastorello, Giacomo De Palma
https://arxiv.org/abs/2508.04498

Efficient classical computation of the neural tangent kernel of quantum neural networks
We propose an efficient classical algorithm to estimate the Neural Tangent Kernel (NTK) associated with a broad class of quantum neural networks. These networks consist of arbitrary unitary operators belonging to the Clifford group interleaved with parametric gates given by the time evolution generated by an arbitrary Hamiltonian belonging to the Pauli group. The proposed algorithm leverages a key insight: the average over the distribution of initialization parameters in the NTK definition can …

Inferring the Graph Structure of Images for Graph Neural Networks
Mayur S Gowda, John Shi, Augusto Santos, Jos\'e M. F. Moura
https://arxiv.org/abs/2509.04677 https://

Inferring the Graph Structure of Images for Graph Neural Networks
Image datasets such as MNIST are a key benchmark for testing Graph Neural Network (GNN) architectures. The images are traditionally represented as a grid graph with each node representing a pixel and edges connecting neighboring pixels (vertically and horizontally). The graph signal is the values (intensities) of each pixel in the image. The graphs are commonly used as input to graph neural networks (e.g., Graph Convolutional Neural Networks (Graph CNNs) [1, 2], Graph Attention Networks (GAT) […

Crosslisted article(s) found for cond-mat.dis-nn. https://arxiv.org/list/cond-mat.dis-nn/new
[1/1]:
- Triadic percolation on multilayer networks
Hanlin Sun, Filippo Radicchi, Ginestra Bianconi

COMponent-Aware Pruning for Accelerated Control Tasks in Latent Space Models
Ganesh Sundaram, Jonas Ulmen, Amjad Haider, Daniel G\"orges
https://arxiv.org/abs/2508.08144 ht…

COMponent-Aware Pruning for Accelerated Control Tasks in Latent Space Models
The rapid growth of resource-constrained mobile platforms, including mobile robots, wearable systems, and Internet-of-Things devices, has increased the demand for computationally efficient neural network controllers (NNCs) that can operate within strict hardware limitations. While deep neural networks (DNNs) demonstrate superior performance in control applications, their substantial computational complexity and memory requirements present significant barriers to practical deployment on edge dev…

Field-theoretic approach to compartmental neuronal networks: impact of dendritic calcium spike-dependent bursting
Audrey O'Brien Teasley, Gabriel Koch Ocker
https://arxiv.org/abs/2508.08405

Field-theoretic approach to compartmental neuronal networks: impact of dendritic calcium spike-dependent bursting
Neurons are spatially extended cells; different parts of a neuron have specific voltage dynamics. Important types of neurons even generate different spikes in different parts of the cell. Neurons' inputs are also often spatially compartmentalized, with different sources targeting different locations on the cell. Classic mean-field theories for neural population activity, however, rely on point-neuron models with at most one type of spike. Here, we develop a statistical field-theoretic approach …

Reconstruction of the depth of the shower maximum of air showers with the SD-750 surface detector of the Pierre Auger Observatory using neural networks
Steffen Hahn (for the Pierre Auger Collaboration)
https://arxiv.org/abs/2509.09328

Reconstruction of the depth of the shower maximum of air showers with the SD-750 surface detector of the Pierre Auger Observatory using neural networks
The origin of ultra-high-energy cosmic rays (UHECRs) is one of the intriguing mysteries in astroparticle physics. In order to identify their sources, we need precise knowledge of the mass composition of UHECRs. The direct detection of UHECRs is not feasible at energies above 0.1 PeV, necessitating the use of mass-sensitive observables of extended air showers induced by UHECRs interacting with the atmosphere. One way to achieve high statistics for these mass-sensitive observables is to use groun…

Efficient Autoregressive Inference for Transformer Probabilistic Models
Conor Hassan, Nasrulloh Loka, Cen-You Li, Daolang Huang, Paul E. Chang, Yang Yang, Francesco Silvestrin, Samuel Kaski, Luigi Acerbi
https://arxiv.org/abs/2510.09477

Efficient Autoregressive Inference for Transformer Probabilistic Models
Transformer-based models for amortized probabilistic inference, such as neural processes, prior-fitted networks, and tabular foundation models, excel at single-pass marginal prediction. However, many real-world applications, from signal interpolation to multi-column tabular predictions, require coherent joint distributions that capture dependencies between predictions. While purely autoregressive architectures efficiently generate such distributions, they sacrifice the flexible set-conditioning…

MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification
Tiantian Yang, Zhiqian Chen
https://arxiv.org/abs/2508.07465 https://arx…

MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification
Integrating multi-omics data, such as DNA methylation, mRNA expression, and microRNA (miRNA) expression, offers a comprehensive view of the biological mechanisms underlying disease. However, the high dimensionality and complex interactions among omics layers present major challenges for predictive modeling. We propose Multi-Omics integration with Tree-generated Graph Neural Network (MOTGNN), a novel and interpretable framework for binary disease classification. MOTGNN employs eXtreme Gradient B…

Crosslisted article(s) found for cs.NE. https://arxiv.org/list/cs.NE/new
[1/1]:
- Decomposer Networks: Deep Component Analysis and Synthesis
Mohsen Joneidi
https:…

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
Jiachen Li, Bang Wu, Xiaoyu Xia, Xiaoning Liu, Xun Yi, Xiuzhen Zhang
https://arxiv.org/abs/2510.06629 …

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
Spiking Neural Networks (SNNs) have gained increasing attention for their superior energy efficiency compared to Artificial Neural Networks (ANNs). However, their security aspects, particularly under backdoor attacks, have received limited attention. Existing defense methods developed for ANNs perform poorly or can be easily bypassed in SNNs due to their event-driven and temporal dependencies. This paper identifies the key blockers that hinder traditional backdoor defenses in SNNs and proposes …

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
Ridiculogram:

Precoder Design in Multi-User FDD Systems with VQ-VAE and GNN
Srikar Allaparapu, Michael Baur, Benedikt B\"ock, Michael Joham, Wolfgang Utschick
https://arxiv.org/abs/2510.09495

Precoder Design in Multi-User FDD Systems with VQ-VAE and GNN
Robust precoding is efficiently feasible in frequency division duplex (FDD) systems by incorporating the learnt statistics of the propagation environment through a generative model. We build on previous work that successfully designed site-specific precoders based on a combination of Gaussian mixture models (GMMs) and graph neural networks (GNNs). In this paper, by utilizing a vector quantized-variational autoencoder (VQ-VAE), we circumvent one of the key drawbacks of GMMs, i.e., the number of …

Multi-Level Service Performance Forecasting via Spatiotemporal Graph Neural Networks
Zhihao Xue, Yun Zi, Nia Qi, Ming Gong, Yujun Zou
https://arxiv.org/abs/2508.07122 https://…

Multi-Level Service Performance Forecasting via Spatiotemporal Graph Neural Networks
This paper proposes a spatiotemporal graph neural network-based performance prediction algorithm to address the challenge of forecasting performance fluctuations in distributed backend systems with multi-level service call structures. The method abstracts system states at different time slices into a sequence of graph structures. It integrates the runtime features of service nodes with the invocation relationships among services to construct a unified spatiotemporal modeling framework. The mode…

Data-Efficient Neural Training with Dynamic Connectomes
Yutong Wu, Peilin He, Tananun Songdechakraiwut
https://arxiv.org/abs/2508.06817 https://arxiv.org/p…

Data-Efficient Neural Training with Dynamic Connectomes
The study of dynamic functional connectomes has provided valuable insights into how patterns of brain activity change over time. Neural networks process information through artificial neurons, conceptually inspired by patterns of activation in the brain. However, their hierarchical structure and high-dimensional parameter space pose challenges for understanding and controlling training dynamics. In this study, we introduce a novel approach to characterize training dynamics in neural networks by…

Physics-Informed Neural Networks in Clean Combustion: A Pathway to Sustainable Aerospace Propulsion
Mahmood Mousavi, Caleb Caldwell, Jacob Baltes, Muteb Aljasem, Bok Jik Lee
https://arxiv.org/abs/2509.08094

Physics-Informed Neural Networks in Clean Combustion: A Pathway to Sustainable Aerospace Propulsion
Achieving clean combustion systems is crucial in terms of solving environmental impacts, decarbonization needs and sustainability matters. Traditional combustion modeling techniques via computational fluid dynamics with accurate chemical kinetics face obstacles in computational cost and accurate representation of turbulence-chemistry interactions. Physically Informed Neural Networks (PINNs) as a new framework, merges physical laws with data-driven learning and shows great potential as an altern…

Expressive Power of Deep Networks on Manifolds: Simultaneous Approximation
Hanfei Zhou, Lei Shi
https://arxiv.org/abs/2509.09362 https://arxiv.org/pdf/2509…

Expressive Power of Deep Networks on Manifolds: Simultaneous Approximation
A key challenge in scientific machine learning is solving partial differential equations (PDEs) on complex domains, where the curved geometry complicates the approximation of functions and their derivatives required by differential operators. This paper establishes the first simultaneous approximation theory for deep neural networks on manifolds. We prove that a constant-depth $\mathrm{ReLU}^{k-1}$ network with bounded weights--a property that plays a crucial role in controlling generalization …

Replaced article(s) found for cond-mat.dis-nn. https://arxiv.org/list/cond-mat.dis-nn/new
[1/1]:
- Frustrated Quantum Magnetism on Complex Networks: What Sets the Total Spin
Preethi Gopalakrishnan, Shovan Dutta

Universal Analog Computation: Fra\"iss\'e limits of dynamical systems
Levin Hornischer
https://arxiv.org/abs/2510.10184 https://arxiv.org/pdf/2510…

Universal Analog Computation: Fraïssé limits of dynamical systems
Analog computation is an alternative to digital computation, that has recently re-gained prominence, since it includes neural networks. Further important examples are cellular automata and differential analyzers. While analog computers offer many advantages, they lack a notion of universality akin to universal digital computers. Since analog computers are best formalized as dynamical systems, we review scattered results on universal dynamical systems, identifying four senses of universality and…

Deep Learning in Astrophysics
Yuan-Sen Ting
https://arxiv.org/abs/2510.10713 https://arxiv.org/pdf/2510.10713

Deep Learning in Astrophysics
Deep learning has generated diverse perspectives in astronomy, with ongoing discussions between proponents and skeptics motivating this review. We examine how neural networks complement classical statistics, extending our data analytical toolkit for modern surveys. Astronomy offers unique opportunities through encoding physical symmetries, conservation laws, and differential equations directly into architectures, creating models that generalize beyond training data. Yet challenges persist as un…

Classical Neural Networks on Quantum Devices via Tensor Network Disentanglers: A Case Study in Image Classification
Borja Aizpurua, Sukhbinder Singh, Rom\'an Or\'us
https://arxiv.org/abs/2509.06653

Classical Neural Networks on Quantum Devices via Tensor Network Disentanglers: A Case Study in Image Classification
We address the problem of implementing bottleneck layers from classical pre-trained neural networks on a quantum computer, with the goal of achieving quantum advantage on near-term devices. Our approach begins with a compression step in which the target linear layer is represented as an effective matrix product operator (MPO) without degrading model performance. The MPO is then further disentangled into a more compact form. This enables a hybrid classical-quantum execution scheme, where the dis…

A Systematic Literature Review of Machine Learning Techniques for Observational Constraints in Cosmology
Luis Rojas, Sebasti\'an Espinoza, Esteban Gonz\'alez, Carlos Maldonado, Fei Luo
https://arxiv.org/abs/2510.09876

A Systematic Literature Review of Machine Learning Techniques for Observational Constraints in Cosmology
This paper presents a systematic literature review focusing on the application of machine learning techniques for deriving observational constraints in cosmology. The goal is to evaluate and synthesize existing research to identify effective methodologies, highlight gaps, and propose future research directions. Our review identifies several key findings: (1) various machine learning techniques, including Bayesian neural networks, Gaussian processes, and deep learning models, have been applied t…

ReBaNO: Reduced Basis Neural Operator Mitigating Generalization Gaps and Achieving Discretization Invariance
Haolan Zheng, Yanlai Chen, Jiequn Han, Yue Yu
https://arxiv.org/abs/2509.09611

ReBaNO: Reduced Basis Neural Operator Mitigating Generalization Gaps and Achieving Discretization Invariance
We propose a novel data-lean operator learning algorithm, the Reduced Basis Neural Operator (ReBaNO), to solve a group of PDEs with multiple distinct inputs. Inspired by the Reduced Basis Method and the recently introduced Generative Pre-Trained Physics-Informed Neural Networks, ReBaNO relies on a mathematically rigorous greedy algorithm to build its network structure offline adaptively from the ground up. Knowledge distillation via task-specific activation function allows ReBaNO to have a comp…

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
Rid…

Functional Connectivity Graph Neural Networks
Yang Li, Luopeiwen Yi, Tananun Songdechakraiwut
https://arxiv.org/abs/2508.05786 https://arxiv.org/pdf/2508.0…

Functional Connectivity Graph Neural Networks
Real-world networks often benefit from capturing both local and global interactions. Inspired by multi-modal analysis in brain imaging, where structural and functional connectivity offer complementary views of network organization, we propose a graph neural network framework that generalizes this approach to other domains. Our method introduces a functional connectivity block based on persistent graph homology to capture global topological features. Combined with structural information, this fo…

Neural Channel Knowledge Map Assisted Scheduling Optimization of Active IRSs in Multi-User Systems
Xintong Chen, Zhenyu Jiang, Jiangbin Lyu, Liqun Fu
https://arxiv.org/abs/2508.07009

Neural Channel Knowledge Map Assisted Scheduling Optimization of Active IRSs in Multi-User Systems
Intelligent Reflecting Surfaces (IRSs) have potential for significant performance gains in next-generation wireless networks but face key challenges, notably severe double-pathloss and complex multi-user scheduling due to hardware constraints. Active IRSs partially address pathloss but still require efficient scheduling in cell-level multi-IRS multi-user systems, whereby the overhead/delay of channel state acquisition and the scheduling complexity both rise dramatically as the user density and …

Intrinsic training dynamics of deep neural networks
Sibylle Marcotte, Gabriel Peyr\'e, R\'emi Gribonval
https://arxiv.org/abs/2508.07370 https://ar…

Intrinsic training dynamics of deep neural networks
A fundamental challenge in the theory of deep learning is to understand whether gradient-based training in high-dimensional parameter spaces can be captured by simpler, lower-dimensional structures, leading to so-called implicit bias. As a stepping stone, we study when a gradient flow on a high-dimensional variable $θ$ implies an intrinsic gradient flow on a lower-dimensional variable $z = ϕ(θ)$, for an architecture-related function $ϕ$. We express a so-called intrinsic dynamic property and…

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
Rid…

Learning Neuron Dynamics within Deep Spiking Neural Networks
Eric Jahns, Davi Moreno, Michel A. Kinsy
https://arxiv.org/abs/2510.07341 https://arxiv.org/pd…

Learning Neuron Dynamics within Deep Spiking Neural Networks
Spiking Neural Networks (SNNs) offer a promising energy-efficient alternative to Artificial Neural Networks (ANNs) by utilizing sparse and asynchronous processing through discrete spike-based computation. However, the performance of deep SNNs remains limited by their reliance on simple neuron models, such as the Leaky Integrate-and-Fire (LIF) model, which cannot capture rich temporal dynamics. While more expressive neuron models exist, they require careful manual tuning of hyperparameters and a…

Modeling bias in decision-making attractor networks
Safaan Sadiq
https://arxiv.org/abs/2508.07471 https://arxiv.org/pdf/2508.07471

Modeling bias in decision-making attractor networks
Attractor neural network models of cortical decision-making circuits represent them as dynamical systems in the state space of neural firing rates with the attractors of the network encoding possible decisions. While the attractors of these models are well studied, far less attention is paid to the basins of attraction even though their sizes can be said to encode the biases towards the corresponding decisions. The parameters of an attractor network control both the attractors and the basins of…

Who Said Neural Networks Aren't Linear?
Nimrod Berman, Assaf Hallak, Assaf Shocher
https://arxiv.org/abs/2510.08570 https://arxiv.org/pdf/2510.08570

Who Said Neural Networks Aren't Linear?
Neural networks are famously nonlinear. However, linearity is defined relative to a pair of vector spaces, $f$$:$$X$$\to$$Y$. Is it possible to identify a pair of non-standard vector spaces for which a conventionally nonlinear function is, in fact, linear? This paper introduces a method that makes such vector spaces explicit by construction. We find that if we sandwich a linear operator $A$ between two invertible neural networks, $f(x)=g_y^{-1}(A g_x(x))$, then the corresponding vector spaces $…

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
Rid…

Sensory robustness through top-down feedback and neural stochasticity in recurrent vision models
Antonino Greco, Marco D'Alessandro, Karl J. Friston, Giovanni Pezzulo, Markus Siegel
https://arxiv.org/abs/2508.07115

Sensory robustness through top-down feedback and neural stochasticity in recurrent vision models
Biological systems leverage top-down feedback for visual processing, yet most artificial vision models succeed in image classification using purely feedforward or recurrent architectures, calling into question the functional significance of descending cortical pathways. Here, we trained convolutional recurrent neural networks (ConvRNN) on image classification in the presence or absence of top-down feedback projections to elucidate the specific computational contributions of those feedback pathw…

Cross-Receiver Generalization for RF Fingerprint Identification via Feature Disentanglement and Adversarial Training
Yuhao Pan, Xiucheng Wang, Nan Cheng, Wenchao Xu
https://arxiv.org/abs/2510.09405

Cross-Receiver Generalization for RF Fingerprint Identification via Feature Disentanglement and Adversarial Training
Radio frequency fingerprint identification (RFFI) is a critical technique for wireless network security, leveraging intrinsic hardware-level imperfections introduced during device manufacturing to enable precise transmitter identification. While deep neural networks have shown remarkable capability in extracting discriminative features, their real-world deployment is hindered by receiver-induced variability. In practice, RF fingerprint signals comprise transmitter-specific features as well as c…

Towards Interpretable Deep Neural Networks for Tabular Data
Khawla Elhadri, J\"org Schl\"otterer, Christin Seifert
https://arxiv.org/abs/2509.08617 https://

Towards Interpretable Deep Neural Networks for Tabular Data
Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce XNNTab, a neural architecture that uses a sparse autoencoder (SAE) to learn a dictionary of monosemantic features within the latent space used for prediction. Using an automated method, we assign human-interpretable semantics to these features. This allows u…

Fourier Learning Machines: Nonharmonic Fourier-Based Neural Networks for Scientific Machine Learning
Mominul Rubel, Adam Meyers, Gabriel Nicolosi
https://arxiv.org/abs/2509.08759

Fourier Learning Machines: Nonharmonic Fourier-Based Neural Networks for Scientific Machine Learning
We introduce the Fourier Learning Machine (FLM), a neural network (NN) architecture designed to represent a multidimensional nonharmonic Fourier series. The FLM uses a simple feedforward structure with cosine activation functions to learn the frequencies, amplitudes, and phase shifts of the series as trainable parameters. This design allows the model to create a problem-specific spectral basis adaptable to both periodic and nonperiodic functions. Unlike previous Fourier-inspired NN models, the …

A Survey of Graph Neural Networks for Drug Discovery: Recent Developments and Challenges
Katherine Berry, Liang Cheng
https://arxiv.org/abs/2509.07887 https://

A Survey of Graph Neural Networks for Drug Discovery: Recent Developments and Challenges
Graph Neural Networks (GNNs) have gained traction in the complex domain of drug discovery because of their ability to process graph-structured data such as drug molecule models. This approach has resulted in a myriad of methods and models in published literature across several categories of drug discovery research. This paper covers the research categories comprehensively with recent papers, namely molecular property prediction, including drug-target binding affinity prediction, drug-drug inter…

Graph-based Integrated Gradients for Explaining Graph Neural Networks
Lachlan Simpson, Kyle Millar, Adriel Cheng, Cheng-Chew Lim, Hong Gunn Chew
https://arxiv.org/abs/2509.07648

Graph-based Integrated Gradients for Explaining Graph Neural Networks
Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discrete structures making IG ill-suited to graphs. In this work, we introduce graph-based integrated gradients (GB-IG); an extension of IG to graphs. We demonstrate on four synthetic datasets that GB-IG accurately identifies crucial structural components of the graph used in classification tasks. We further demonstrate on t…

Homogenization with Guaranteed Bounds via Primal-Dual Physically Informed Neural Networks
Liya Gaynutdinova, Martin Do\v{s}k\'a\v{r}, Ond\v{r}ej Roko\v{s}, Ivana Pultarov\'a
https://arxiv.org/abs/2509.07579

Homogenization with Guaranteed Bounds via Primal-Dual Physically Informed Neural Networks
Physics-informed neural networks (PINNs) have shown promise in solving partial differential equations (PDEs) relevant to multiscale modeling, but they often fail when applied to materials with discontinuous coefficients, such as media with piecewise constant properties. This paper introduces a dual formulation for the PINN framework to improve the reliability of the homogenization of periodic thermo-conductive composites, for both strong and variational (weak) formulations. The dual approach fa…

Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement
Jakob Nyberg, Pontus Johnson
https://arxiv.org/abs/2509.09219 https://…

Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement
We present and evaluate Vejde; a framework which combines data abstraction, graph neural networks and reinforcement learning to produce inductive policy functions for decision problems with richly structured states, such as object classes and relations. MDP states are represented as data bases of facts about entities, and Vejde converts each state to a bipartite graph, which is mapped to latent states through neural message passing. The factored representation of both states and actions allows …

An in-depth look at approximation via deep and narrow neural networks
Joris Dommel, Sven A. Wegner
https://arxiv.org/abs/2510.07202 https://arxiv.org/pdf/2…

An in-depth look at approximation via deep and narrow neural networks
In 2017, Hanin and Sellke showed that the class of arbitrarily deep, real-valued, feed-forward and ReLU-activated networks of width w forms a dense subset of the space of continuous functions on R^n, with respect to the topology of uniform convergence on compact sets, if and only if w>n holds. To show the necessity, a concrete counterexample function f:R^n->R was used. In this note we actually approximate this very f by neural networks in the two cases w=n and w=n+1 around the aforementioned th…

Are Heterogeneous Graph Neural Networks Truly Effective? A Causal Perspective
Xiao Yang, Xuejiao Zhao, Zhiqi Shen
https://arxiv.org/abs/2510.05750 https://…

Are Heterogeneous Graph Neural Networks Truly Effective? A Causal Perspective
Graph neural networks (GNNs) have achieved remarkable success in node classification. Building on this progress, heterogeneous graph neural networks (HGNNs) integrate relation types and node and edge semantics to leverage heterogeneous information. Causal analysis for HGNNs is advancing rapidly, aiming to separate genuine causal effects from spurious correlations. However, whether HGNNs are intrinsically effective remains underexamined, and most studies implicitly assume rather than establish t…

Heart Disease Prediction: A Comparative Study of Optimisers Performance in Deep Neural Networks
Chisom Chibuike, Adeyinka Ogunsanya
https://arxiv.org/abs/2509.08499 https://

Heart Disease Prediction: A Comparative Study of Optimisers Performance in Deep Neural Networks
Optimization has been an important factor and topic of interest in training deep learning models, yet less attention has been given to how we select the optimizers we use to train these models. Hence, there is a need to dive deeper into how we select the optimizers we use for training and the metrics that determine this selection. In this work, we compare the performance of 10 different optimizers in training a simple Multi-layer Perceptron model using a heart disease dataset from Kaggle. We se…

Compressing CNN models for resource-constrained systems by channel and layer pruning
Ahmed Sadaqa, Di Liu
https://arxiv.org/abs/2509.08714 https://arxiv.or…

Compressing CNN models for resource-constrained systems by channel and layer pruning
Convolutional Neural Networks (CNNs) have achieved significant breakthroughs in various fields. However, these advancements have led to a substantial increase in the complexity and size of these networks. This poses a challenge when deploying large and complex networks on edge devices. Consequently, model compression has emerged as a research field aimed at reducing the size and complexity of CNNs. One prominent technique in model compression is model pruning. This paper will present a new tech…

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…

An Interpretable Deep Learning Model for General Insurance Pricing
Patrick J. Laub, Tu Pho, Bernard Wong
https://arxiv.org/abs/2509.08467 https://arxiv.org…

An Interpretable Deep Learning Model for General Insurance Pricing
This paper introduces the Actuarial Neural Additive Model, an inherently interpretable deep learning model for general insurance pricing that offers fully transparent and interpretable results while retaining the strong predictive power of neural networks. This model assigns a dedicated neural network (or subnetwork) to each individual covariate and pairwise interaction term to independently learn its impact on the modeled output while implementing various architectural constraints to allow for…

QGraphLIME - Explaining Quantum Graph Neural Networks
Haribandhu Jena, Jyotirmaya Shivottam, Subhankar Mishra
https://arxiv.org/abs/2510.05683 https://arxi…

QGraphLIME - Explaining Quantum Graph Neural Networks
Quantum graph neural networks offer a powerful paradigm for learning on graph-structured data, yet their explainability is complicated by measurement-induced stochasticity and the combinatorial nature of graph structure. In this paper, we introduce QuantumGraphLIME (QGraphLIME), a model-agnostic, post-hoc framework that treats model explanations as distributions over local surrogates fit on structure-preserving perturbations of a graph. By aggregating surrogate attributions together with their …