Tootfinder

An open dataset of neural networks for hypernetwork research
David Kurtenbach, Lior Shamir
https://arxiv.org/abs/2507.15869 https://a…

An open dataset of neural networks for hypernetwork research
Despite the transformative potential of AI, the concept of neural networks that can produce other neural networks by generating model weights (hypernetworks) has been largely understudied. One of the possible reasons is the lack of available research resources that can be used for the purpose of hypernetwork research. Here we describe a dataset of neural networks, designed for the purpose of hypernetworks research. The dataset includes $10^4$ LeNet-5 neural networks trained for binary image cla…

Using Modular Arithmetic Optimized Neural Networks To Crack Affine Cryptographic Schemes Efficiently
Vanja Stojanovi\'c, \v{Z}iga Lesar, CIril Bohak
https://arxiv.org/abs/2507.14229

Using Modular Arithmetic Optimized Neural Networks To Crack Affine Cryptographic Schemes Efficiently
We investigate the cryptanalysis of affine ciphers using a hybrid neural network architecture that combines modular arithmetic-aware and statistical feature-based learning. Inspired by recent advances in interpretable neural networks for modular arithmetic and neural cryptanalysis of classical ciphers, our approach integrates a modular branch that processes raw ciphertext sequences and a statistical branch that leverages letter frequency features. Experiments on datasets derived from natural En…

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 in Memristive Neural Networks
H. M. Heidema, H. J. van Waarde, B. Besselink
https://arxiv.org/abs/2507.15324 https://arxiv.o…

Learning in Memristive Neural Networks
Memristors are nonlinear two-terminal circuit elements whose resistance at a given time depends on past electrical stimuli. Recently, networks of memristors have received attention in neuromorphic computing since they can be used to implement Artificial Neural Networks (ANNs) in hardware. For this, one can use a class of memristive circuits called crossbar arrays. In this paper, we describe a circuit implementation of an ANN and resolve three questions concerning such an implementation. In part…

Brain-inspired interpretable reservoir computing with resonant recurrent neural networks
Mark A. Kramer
https://arxiv.org/abs/2506.17083 https://

Brain-inspired interpretable reservoir computing with resonant recurrent neural networks
Traditional artificial neural networks consist of nodes with non-oscillatory dynamics. Biological neural networks, on the other hand, consist of oscillatory components embedded in an oscillatory environment. Motivated by this feature of biological neurons, we describe a reservoir computing framework with explicit damped, oscillatory node dynamics. We express the oscillatory dynamics using two history dependent terms to connect these dynamics with existing artificial neural network approaches an…

Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks
Marcel Kleinmann, Shashank Agnihotri, Margret Keuper
https://arxiv.org/abs/2507.16761

Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks
Faithfulness and interpretability are essential for deploying deep neural networks (DNNs) in safety-critical domains such as medical imaging. B-cos networks offer a promising solution by replacing standard linear layers with a weight-input alignment mechanism, producing inherently interpretable, class-specific explanations without post-hoc methods. While maintaining diagnostic performance competitive with state-of-the-art DNNs, standard B-cos models suffer from severe aliasing artifacts in thei…

JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs
Zhiqiang Que, Chang Sun, Sudarshan Paramesvaran, Emyr Clement, Katerina Karakoulaki, Christopher Brown, Lauri Laatu, Arianna Cox, Alexander Tapper, Wayne Luk, Maria Spiropulu
https://arxiv.org/abs/2508.15468

JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs
Graph Neural Networks (GNNs), particularly Interaction Networks (INs), have shown exceptional performance for jet tagging at the CERN High-Luminosity Large Hadron Collider (HL-LHC). However, their computational complexity and irregular memory access patterns pose significant challenges for deployment on FPGAs in hardware trigger systems, where strict latency and resource constraints apply. In this work, we propose JEDI-linear, a novel GNN architecture with linear computational complexity that e…

Continual Learning with Columnar Spiking Neural Networks
Denis Larionov, Nikolay Bazenkov, Mikhail Kiselev
https://arxiv.org/abs/2506.17169 https://…

Continual Learning with Columnar Spiking Neural Networks
This study investigates columnar-organized spiking neural networks (SNNs) for continual learning and catastrophic forgetting. Using CoLaNET (Columnar Layered Network), we show that microcolumns adapt most efficiently to new tasks when they lack shared structure with prior learning. We demonstrate how CoLaNET hyperparameters govern the trade-off between retaining old knowledge (stability) and acquiring new information (plasticity). Our optimal configuration learns ten sequential MNIST tasks effe…

Physics-Informed Neural Networks for High-Precision Grad-Shafranov Equilibrium Reconstruction
Cuizhi Zhou, Kaien Zhu
https://arxiv.org/abs/2507.16636 https…

Physics-Informed Neural Networks for High-Precision Grad-Shafranov Equilibrium Reconstruction
The equilibrium reconstruction of plasma is a core step in real-time diagnostic tasks in fusion research. This paper explores a multi-stage Physics-Informed Neural Networks(PINNs) approach to solve the Grad-Shafranov equation, achieving high-precision solutions with an error magnitude of $O(10^{-8})$ between the output of the second-stage neural network and the analytical solution. Our results demonstrate that the multi-stage PINNs provides a reliable tool for plasma equilibrium reconstruction.

Tree-like Pairwise Interaction Networks
Ronald Richman, Salvatore Scognamiglio, Mario V. W\"uthrich
https://arxiv.org/abs/2508.15678 https://arxiv.org…

Tree-like Pairwise Interaction Networks
Modeling feature interactions in tabular data remains a key challenge in predictive modeling, for example, as used for insurance pricing. This paper proposes the Tree-like Pairwise Interaction Network (PIN), a novel neural network architecture that explicitly captures pairwise feature interactions through a shared feed-forward neural network architecture that mimics the structure of decision trees. PIN enables intrinsic interpretability by design, allowing for direct inspection of interaction e…

CPED-NCBFs: A Conformal Prediction for Expert Demonstration-based Neural Control Barrier Functions
Sumeadh MS, Kevin Dsouza, Ravi Prakash
https://arxiv.org/abs/2507.15022

CPED-NCBFs: A Conformal Prediction for Expert Demonstration-based Neural Control Barrier Functions
Among the promising approaches to enforce safety in control systems, learning Control Barrier Functions (CBFs) from expert demonstrations has emerged as an effective strategy. However, a critical challenge remains: verifying that the learned CBFs truly enforce safety across the entire state space. This is especially difficult when CBF is represented using neural networks (NCBFs). Several existing verification techniques attempt to address this problem including SMT-based solvers, mixed-integer …

Neural Network Acceleration of Iterative Methods for Nonlinear Schr\"odinger Eigenvalue Problems
Daniel Peterseim, Jan-F. Pietschmann, Jonas P\"uschel, Kilian Ruess
https://arxiv.org/abs/2507.16349

Neural Network Acceleration of Iterative Methods for Nonlinear Schrödinger Eigenvalue Problems
We present a novel approach to accelerate iterative methods to solve nonlinear Schrödinger eigenvalue problems using neural networks. Nonlinear eigenvector problems are fundamental in quantum mechanics and other fields, yet conventional solvers often suffer from slow convergence in extreme parameter regimes, as exemplified by the rotating Bose- Einstein condensate (BEC) problem. Our method uses a neural network to predict and refine solution trajectories, leveraging knowledge from previous sim…

Conditionally adaptive augmented Lagrangian method for physics-informed learning of forward and inverse problems using artificial neural networks
Qifeng Hu, Shamsulhaq Basir, Inanc Senocak
https://arxiv.org/abs/2508.15695

Conditionally adaptive augmented Lagrangian method for physics-informed learning of forward and inverse problems using artificial neural networks
We present several advances to the physics and equality constrained artificial neural networks (PECANN) framework that substantially improve its capability to learn solutions of canonical partial differential equations (PDEs). First, we generalize the augmented Lagrangian method (ALM) to support multiple independent penalty parameters, enabling simultaneous enforcement of heterogeneous constraints. Second, we reformulate pointwise constraint enforcement and Lagrange multipliers as expectations …

Hessian-based lightweight neural network for brain vessel segmentation on a minimal training dataset
Alexandra Bernadotte, Elfimov Nikita, Mikhail Shutov, Ivan Menshikov
https://arxiv.org/abs/2508.15660

Hessian-based lightweight neural network for brain vessel segmentation on a minimal training dataset
Accurate segmentation of blood vessels in brain magnetic resonance angiography (MRA) is essential for successful surgical procedures, such as aneurysm repair or bypass surgery. Currently, annotation is primarily performed through manual segmentation or classical methods, such as the Frangi filter, which often lack sufficient accuracy. Neural networks have emerged as powerful tools for medical image segmentation, but their development depends on well-annotated training datasets. However, there i…

Enabling Efficient Hardware Acceleration of Hybrid Vision Transformer (ViT) Networks at the Edge
Joren Dumoulin, Pouya Houshmand, Vikram Jain, Marian Verhelst
https://arxiv.org/abs/2507.14651

Enabling Efficient Hardware Acceleration of Hybrid Vision Transformer (ViT) Networks at the Edge
Hybrid vision transformers combine the elements of conventional neural networks (NN) and vision transformers (ViT) to enable lightweight and accurate detection. However, several challenges remain for their efficient deployment on resource-constrained edge devices. The hybrid models suffer from a widely diverse set of NN layer types and large intermediate data tensors, hampering efficient hardware acceleration. To enable their execution at the edge, this paper proposes innovations across the har…

Advancing atomic electron tomography with neural networks
Juhyeok Lee, Yongsoo Yang
https://arxiv.org/abs/2506.16104 https://arxiv.or…

Advancing atomic electron tomography with neural networks
Accurate determination of three-dimensional (3D) atomic structures is crucial for understanding and controlling the properties of nanomaterials. Atomic electron tomography (AET) offers non-destructive atomic imaging with picometer-level precision, enabling the resolution of defects, interfaces, and strain fields in 3D, as well as the observation of dynamic structural evolution. However, reconstruction artifacts arising from geometric limitations and electron dose constraints can hinder reliable…

Learning Null Geodesics for Gravitational Lensing Rendering in General Relativity
Mingyuan Sun, Zheng Fang, Jiaxu Wang, Kunyi Zhang, Qiang Zhang, Renjing Xu
https://arxiv.org/abs/2507.15775

Learning Null Geodesics for Gravitational Lensing Rendering in General Relativity
We present GravLensX, an innovative method for rendering black holes with gravitational lensing effects using neural networks. The methodology involves training neural networks to fit the spacetime around black holes and then employing these trained models to generate the path of light rays affected by gravitational lensing. This enables efficient and scalable simulations of black holes with optically thin accretion disks, significantly decreasing the time required for rendering compared to tra…

Edge Intelligence with Spiking Neural Networks
Shuiguang Deng, Di Yu, Changze Lv, Xin Du, Linshan Jiang, Xiaofan Zhao, Wentao Tong, Xiaoqing Zheng, Weijia Fang, Peng Zhao, Gang Pan, Schahram Dustdar, Albert Y. Zomaya
https://arxiv.org/abs/2507.14069

Edge Intelligence with Spiking Neural Networks
The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational resources and centralized data management, the resulting latency, bandwidth consumption, and privacy concerns have exposed critical limitations in cloud-centric paradigms. Brain-inspired computing, particularly Spiking Neural Networks (SNNs), offers a promisin…

A Statistician's Overview of Mechanistic-Informed Modeling
Christopher K. Wikle, Joshua North, Giri Gopalan, Myungsoo Yoo
https://arxiv.org/abs/2507.14336

A Statistician's Overview of Mechanistic-Informed Modeling
The recent success of deep neural network models with physical constraints (so-called, Physics-Informed Neural Networks, PINNs) has led to renewed interest in the incorporation of mechanistic information in predictive models. Statisticians and others have long been interested in this problem, which has led to several practical and innovative solutions dating back decades. In this overview, we focus on the problem of data-driven prediction and inference of dynamic spatio-temporal processes that …

HIP: Model-Agnostic Hypergraph Influence Prediction via Distance-Centrality Fusion and Neural ODEs
Su-Su Zhang, JinFeng Xie, Yang Chen, Min Gao, Cong Li, Chuang Liu, Xiu-Xiu Zhan
https://arxiv.org/abs/2508.15312

HIP: Model-Agnostic Hypergraph Influence Prediction via Distance-Centrality Fusion and Neural ODEs
Predicting user influence in social networks is a critical problem, and hypergraphs, as a prevalent higher-order modeling approach, provide new perspectives for this task. However, the absence of explicit cascade or infection probability data makes it particularly challenging to infer influence in hypergraphs. To address this, we introduce HIP, a unified and model-independent framework for influence prediction without knowing the underlying spreading model. HIP fuses multi-dimensional centralit…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/5]:
- Quantized Neural Networks for Microcontrollers: A Comprehensive Review of Methods, Platforms, and...
Hamza A. Abushahla, Dara Varam, Ariel J. N. Panopio, Mohamed I. AlHajri

Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
Ziqiao Yu, Pengfei Sun, Dan F. M. Goodman
https://arxiv.org/abs/2507.16043 https:…

Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
We investigate the extent to which Spiking Neural Networks (SNNs) trained with Surrogate Gradient Descent (Surrogate GD), with and without delay learning, can learn from precise spike timing beyond firing rates. We first design synthetic tasks isolating intra-neuron inter-spike intervals and cross-neuron synchrony under matched spike counts. On more complex spike-based speech recognition datasets (Spiking Heidelberg Digits (SHD) and Spiking Speech Commands (SSC), we construct variants where spi…

Multi-fidelity Ensemble Kalman Filter algorithms enhanced by Convolutional Neural Networks
Tom Moussie, Paolo Errante, Marcello Meldi
https://arxiv.org/abs/2507.13744

Multi-fidelity Ensemble Kalman Filter algorithms enhanced by Convolutional Neural Networks
The present research work proposes advancement for Data Assimilation strategies using Convolutional Neural Networks (CNN). More precisely, multi-fidelity and multi-level algorithms for the Ensemble Kalman Filter are enhanced by CNN tools, with the objective to reduce the discrepancy in the prediction between ensemble realizations performed with different models. The proposed methodology is assessed via the analysis of the flow through a cascade of NACA 0012 profiles for Reynolds $Re=1\,000$ and…

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…

Genuine multipartite entanglement verification with convolutional neural networks
Yi-Jun Luo, Xuan Leng, Chengjie Zhang
https://arxiv.org/abs/2508.13463 https://

Genuine multipartite entanglement verification with convolutional neural networks
In recent years, the detection of genuine multipartite entanglement (GME) via machine learning has received scant attention. Here, we employ convolutional neural networks (CNNs), as well as CNNs enhanced with squeeze-and-excitation (SE) to detect GME. We randomly generated GME states with 4 to 6 qubits and GHZ-diagonal states ranging from 4 to 20 qubits using the semidefinite programming approach. Subsequently, we assessed their classification accuracy. Our results demonstrate that the integrat…

Crosslisted article(s) found for cs.PL. https://arxiv.org/list/cs.PL/new
[1/1]:
- Mini-Batch Robustness Verification of Deep Neural Networks
Saar Tzour-Shaday, Dana Drachsler Cohen

Categorical Construction of Logically Verifiable Neural Architectures
Logan Nye
https://arxiv.org/abs/2508.11647 https://arxiv.org/pdf/2508.11647

Categorical Construction of Logically Verifiable Neural Architectures
Neural networks excel at pattern recognition but struggle with reliable logical reasoning, often violating basic logical principles during inference. We address this limitation by developing a categorical framework that systematically constructs neural architectures with provable logical guarantees. Our approach treats logical theories as algebraic structures called Lawvere theories, which we transform into neural networks using categorical algebra in the 2-category of parametric maps. Unlike e…

SMTrack: End-to-End Trained Spiking Neural Networks for Multi-Object Tracking in RGB Videos
Pengzhi Zhong, Xinzhe Wang, Dan Zeng, Qihua Zhou, Feixiang He, Shuiwang Li
https://arxiv.org/abs/2508.14607

SMTrack: End-to-End Trained Spiking Neural Networks for Multi-Object Tracking in RGB Videos
Brain-inspired Spiking Neural Networks (SNNs) exhibit significant potential for low-power computation, yet their application in visual tasks remains largely confined to image classification, object detection, and event-based tracking. In contrast, real-world vision systems still widely use conventional RGB video streams, where the potential of directly-trained SNNs for complex temporal tasks such as multi-object tracking (MOT) remains underexplored. To address this challenge, we propose SMTrack…

This https://arxiv.org/abs/2505.15588 has been replaced.
initial toot: https://mastoxiv.page/@arX…

EPBench: A Benchmark for Short-term Earthquake Prediction with Neural Networks
Since the beginning of this century, the significant advancements in artificial intelligence and neural networks have offered the potential to bring new transformations to short-term earthquake prediction research. However, currently, there is no widely used benchmark for this task. To address this, we have built a new benchmark (EPBench), which is, to our knowledge, the first global regional-scale short-term earthquake prediction benchmark. Our benchmark comprises 924,472 earthquake records an…

Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph
Mengyang Cao, Frank F. Yang, Yi Jin, Yijun Yan
https://arxiv.org/abs/2508.14059 https://

Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph
Identifying relevant information among massive volumes of data is a challenge for modern recommendation systems. Graph Neural Networks (GNNs) have demonstrated significant potential by utilizing structural and semantic relationships through graph-based learning. This study assessed the abilities of four GNN architectures, LightGCN, GraphSAGE, GAT, and PinSAGE, on the Amazon Product Co-purchase Network under link prediction settings. We examined practical trade-offs between architectures, model …

Theory-informed neural networks for particle physics
Barry M. Dillon, Michael Spannowsky
https://arxiv.org/abs/2507.13447 https://arx…

Theory-informed neural networks for particle physics
We present a theory-informed reinforcement-learning framework that recasts the combinatorial assignment of final-state particles in hadron collider events as a Markov decision process. A transformer-based Deep Q-Network, rewarded at each step by the logarithmic change in the tree-level matrix element, learns to map final-state particles to partons. Because the reward derives solely from first-principles theory, the resulting policy is label-free and fully interpretable, allowing every reconstru…

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…

Simulation of parametrized cardiac electrophysiology in three dimensions using physics-informed neural networks
Roshan Antony Gomez, Julien St\"ocker, Bar{\i}\c{s} Cans{\i}z, Michael Kaliske
https://arxiv.org/abs/2506.15405

Simulation of parametrized cardiac electrophysiology in three dimensions using physics-informed neural networks
Physics-informed neural networks (PINNs) are extensively used to represent various physical systems across multiple scientific domains. The same can be said for cardiac electrophysiology, wherein fully-connected neural networks (FCNNs) have been employed to predict the evolution of an action potential in a 2D space following the two-parameter phenomenological Aliev-Panfilov (AP) model. In this paper, the training behaviour of PINNs is investigated to determine optimal hyperparameters to predict…

Replaced article(s) found for astro-ph.SR. https://arxiv.org/list/astro-ph.SR/new
[1/1]:
- Nuclear Neural Networks: Emulating Late Burning Stages in Core Collapse Supernova Progenitors
Grichener, Renzo, Kerzendorf, Farmer, de Mink, Bellinger, Chan, Chen, Farag, Justham

Researchers detail All-Topographic Neural Networks, claiming they better mimic human spatial biases and consume less energy than other machine vision networks (Matthew S. Smith/IEEE Spectrum)
https://spectrum.ieee.org/topographic-neural-network

Topographic Neural Networks Help AI See Like a Human
All-TNN networks mimic human vision and consume less energy than CNNs. Curious how they achieve this? Dive into the details.

Siamese Neural Network for Label-Efficient Critical Phenomena Prediction in 3D Percolation Models
Shanshan Wang, Dian Xu, Jianmin Shen, Feng Gao, Wei Li, Weibing Deng
https://arxiv.org/abs/2507.14159

Siamese Neural Network for Label-Efficient Critical Phenomena Prediction in 3D Percolation Models
Percolation theory serves as a cornerstone for studying phase transitions and critical phenomena, with broad implications in statistical physics, materials science, and complex networks. However, most machine learning frameworks for percolation analysis have focused on two-dimensional systems, oversimplifying the spatial correlations and morphological complexity of real-world three-dimensional materials. To bridge this gap and improve label efficiency and scalability in 3D systems, we propose a…

Physics-guided gated recurrent units for inversion-based feedforward control
Mingdao Lin, Max Bolderman, Mircea Lazar
https://arxiv.org/abs/2507.14052 http…

Physics-guided gated recurrent units for inversion-based feedforward control
Inversion-based feedforward control relies on an accurate model that describes the inverse system dynamics. The gated recurrent unit (GRU), which is a recent architecture in recurrent neural networks, is a strong candidate for obtaining such a model from data. However, due to their black-box nature, GRUs face challenges such as limited interpretability and vulnerability to overfitting. Recently, physics-guided neural networks (PGNNs) have been introduced, which integrate the prior physical mode…

Numerical Analysis of Unsupervised Learning Approaches for Parameter Identification in PDEs
Siyu Cen, Bangti Jin, Qimeng Quan, Zhi Zhou
https://arxiv.org/abs/2508.15381 https://…

Numerical Analysis of Unsupervised Learning Approaches for Parameter Identification in PDEs
Identifying parameters in partial differential equations (PDEs) represents a very broad class of applied inverse problems. In recent years, several unsupervised learning approaches using (deep) neural networks have been developed to solve PDE parameter identifications. These approaches employ neural networks as ansatz functions to approximate the parameters and / or the states, and have demonstrated impressive empirical performance. In this paper, we provide a comprehensive survey on these unsu…

Cosmology-informed Neural Networks to infer dark energy equation-of-state
Anshul Verma, Shashwat Sourav, Pavan K. Aluri, David F. Mota
https://arxiv.org/abs/2508.12032 https://

Cosmology-informed Neural Networks to infer dark energy equation-of-state
We present a framework that combines physics-informed neural networks (PINNs) with Markov Chain Monte Carlo (MCMC) inference to constrain dynamical dark energy models using the Pantheon+ Type Ia supernova compilation. First, we train a physics-informed neural network to learn the solution of the Friedmann equation and accurately reproduce the matter density term x_m(z) = Omega_m,0 (1+z)^3 across a range of Omega_m,0. For each of five two-parameter equation-of-state (EoS) forms: Chevallier-Polar…

Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network
Mahin Montasir Afif, Abdullah Al Noman, K. M. Tahsin Kabir, Md. Mortuza Ahmmed, Md. Mostafizur Rahman, Mufti Mahmud, Md. Ashraful Babu
https://arxiv.org/abs/2506.17165

Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network
Generative Adversarial Networks (GAN) have shown potential in expanding limited medical imaging datasets. This study explores how different ratios of GAN-generated and real brain tumor MRI images impact the performance of a CNN in classifying healthy vs. tumorous scans. A DCGAN was used to create synthetic images which were mixed with real ones at various ratios to train a custom CNN. The CNN was then evaluated on a separate real-world test set. Our results indicate that the model maintains hig…

Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models
Aaron Ho (MIT Plasma Science and Fusion Center, Cambridge, USA), Lorenzo Zanisi (UKAEA Culham Centre for Fusion Energy, Abingdon, UK), Bram de Leeuw (Radboud University, Nijmegen, Netherlands), Vincent Galvan (MIT Plasma Science and Fusion Center, Cambridge, USA), Pablo Rodriguez-Fernandez (MIT Plasma Science and Fusion Center, Cambridge, USA), Nath…

Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models
This work demonstrates a proof-of-principle for using uncertainty-aware architectures, in combination with active learning techniques and an in-the-loop physics simulation code as a data labeller, to construct efficient datasets for data-driven surrogate model generation. Building off of a previous proof-of-principle successfully demonstrating training set reduction on static pre-labelled datasets, using the ADEPT framework, this strategy was applied again to the plasma turbulent transport prob…

1T'-MoTe$_2$ as an integrated saturable absorber for photonic machine learning
Maria Carolina Volpato, Henrique G. Rosa, Tom Reep, Pierre-Louis de Assis, Newton Cesario Frateschi
https://arxiv.org/abs/2507.16140

1T'-MoTe$_2$ as an integrated saturable absorber for photonic machine learning
We investigate the saturable absorption behavior of a 1T'-MoTe$_2$ monolayer integrated with a silicon nitride waveguide for applications in photonic neural networks. Using experimental transmission measurements and theoretical modeling, we characterize the nonlinear response of the material. Our model, incorporating quasi-Fermi level separation and carrier dynamics, successfully explains these behaviors and predicts the material's absorption dependence on the carrier density. Furthermore, we d…

Let's Grow an Unbiased Community: Guiding the Fairness of Graphs via New Links
Jiahua Lu, Huaxiao Liu, Shuotong Bai, Junjie Xu, Renqiang Luo, Enyan Dai
https://arxiv.org/abs/2508.15499

Let's Grow an Unbiased Community: Guiding the Fairness of Graphs via New Links
Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications. However, due to the biases in the graph structures, graph neural networks face significant challenges in fairness. Although the original user graph structure is generally biased, it is promising to guide these existing structures toward unbiased ones by introducing new links. The fairness guidance via new links could foster unbiased communities, thereby enhancing fairness in downstream applications. To ad…

High-Frequency First: A Two-Stage Approach for Improving Image INR
Sumit Kumar Dam, Mrityunjoy Gain, Eui-Nam Huh, Choong Seon Hong
https://arxiv.org/abs/2508.15582 https://

High-Frequency First: A Two-Stage Approach for Improving Image INR
Implicit Neural Representations (INRs) have emerged as a powerful alternative to traditional pixel-based formats by modeling images as continuous functions over spatial coordinates. A key challenge, however, lies in the spectral bias of neural networks, which tend to favor low-frequency components while struggling to capture high-frequency (HF) details such as sharp edges and fine textures. While prior approaches have addressed this limitation through architectural modifications or specialized …

MorphoNAS: Embryogenic Neural Architecture Search Through Morphogen-Guided Development
Mykola Glybovets, Sergii Medvid
https://arxiv.org/abs/2507.13785 htt…

MorphoNAS: Embryogenic Neural Architecture Search Through Morphogen-Guided Development
While biological neural networks develop from compact genomes using relatively simple rules, modern artificial neural architecture search methods mostly involve explicit and routine manual work. In this paper, we introduce MorphoNAS (Morphogenetic Neural Architecture Search), a system able to deterministically grow neural networks through morphogenetic self-organization inspired by the Free Energy Principle, reaction-diffusion systems, and gene regulatory networks. In MorphoNAS, simple genomes …

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…

Identification and Denoising of Radio Signals from Cosmic-Ray Air Showers using Convolutional Neural Networks
R. Abbasi, et al.
https://arxiv.org/abs/2508.14711 https://

Identification and Denoising of Radio Signals from Cosmic-Ray Air Showers using Convolutional Neural Networks
Radio pulses generated by cosmic-ray air showers can be used to reconstruct key properties like the energy and depth of the electromagnetic component of cosmic-ray air showers. Radio detection threshold, influenced by natural and anthropogenic radio background, can be reduced through various techniques. In this work, we demonstrate that convolutional neural networks (CNNs) are an effective way to lower the threshold. We developed two CNNs: a classifier to distinguish radio signal waveforms from…

Replaced article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[1/1]:
- Neural reproducing kernel Banach spaces and representer theorems for deep networks
Francesca Bartolucci, Ernesto De Vito, Lorenzo Rosasco, Stefano Vigogna

Replaced article(s) found for cs.CR. https://arxiv.org/list/cs.CR/new
[1/2]:
- A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks
Farzad Nikfam, Raffaele Casaburi, Alberto Marchisio, Maurizio Martina, Muhammad Shafique

Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators
Xiang Cao, Qiaoqiao Ding, Xinliang Liu, Lei Zhang, Xiaoqun Zhang
https://arxiv.org/abs/2507.16344

Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators
Ultrasound Computed Tomography (USCT) constitutes a nonlinear inverse problem with inherent ill-posedness that can benefit from regularization through diffusion generative priors. However, traditional approaches for solving Helmholtz equation-constrained USCT face three fundamental challenges when integrating these priors: PDE-constrained gradient computation, discretization-induced approximation errors, and computational imbalance between neural networks and numerical PDE solvers. In this work…

Learning from user's behaviour of some well-known congested traffic networks
Isolda Cardoso, Lucas Venturato, Jorgelina Walpen
https://arxiv.org/abs/2508.14804 https://

Learning from user's behaviour of some well-known congested traffic networks
We consider the problem of predicting users' behavior of a congested traffic network under an equilibrium condition, the traffic assignment problem. We propose a two-stage machine learning approach which couples a neural network with a fixed point algorithm, and we evaluate its performance along several classical congested traffic networks.

Lookup Table-based Multiplication-free All-digital DNN Accelerator Featuring Self-Synchronous Pipeline Accumulation
Hiroto Tagata, Takashi Sato, Hiromitsu Awano
https://arxiv.org/abs/2506.16800

Lookup Table-based Multiplication-free All-digital DNN Accelerator Featuring Self-Synchronous Pipeline Accumulation
Deep neural networks (DNNs) have been widely applied in our society, yet reducing power consumption due to large-scale matrix computations remains a critical challenge. MADDNESS is a known approach to improving energy efficiency by substituting matrix multiplication with table lookup operations. Previous research has employed large analog computing circuits to convert inputs into LUT addresses, which presents challenges to area efficiency and computational accuracy. This paper proposes a novel …

Improving Fairness in Graph Neural Networks via Counterfactual Debiasing
Zengyi Wo, Chang Liu, Yumeng Wang, Minglai Shao, Wenjun Wang
https://arxiv.org/abs/2508.14683 https://…

Improving Fairness in Graph Neural Networks via Counterfactual Debiasing
Graph Neural Networks (GNNs) have been successful in modeling graph-structured data. However, similar to other machine learning models, GNNs can exhibit bias in predictions based on attributes like race and gender. Moreover, bias in GNNs can be exacerbated by the graph structure and message-passing mechanisms. Recent cutting-edge methods propose mitigating bias by filtering out sensitive information from input or representations, like edge dropping or feature masking. Yet, we argue that such st…

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:

Leveraging Quantum Layers in Classical Neural Networks
Silvie Ill\'esov\'a
https://arxiv.org/abs/2507.12505 https://arxiv.org…

Leveraging Quantum Layers in Classical Neural Networks
Hybrid quantum-classical neural networks represent a promising frontier in the search for improved machine learning models. This thesis explores the integration of quantum layers within classical convolutional neural network architectures, aiming to leverage quantum entanglement and feature mapping to enhance learning capabilities. A detailed methodology for constructing and training such hybrid models is presented, using PyTorch and Qiskit Machine Learning frameworks. Experiments investigate t…

A Study of Hybrid and Evolutionary Metaheuristics for Single Hidden Layer Feedforward Neural Network Architecture
Gautam Siddharth Kashyap, Md Tabrez Nafis, Samar Wazir
https://arxiv.org/abs/2506.15737

A Study of Hybrid and Evolutionary Metaheuristics for Single Hidden Layer Feedforward Neural Network Architecture
Training Artificial Neural Networks (ANNs) with Stochastic Gradient Descent (SGD) frequently encounters difficulties, including substantial computing expense and the risk of converging to local optima, attributable to its dependence on partial weight gradients. Therefore, this work investigates Particle Swarm Optimization (PSO) and Genetic Algorithms (GAs) - two population-based Metaheuristic Optimizers (MHOs) - as alternatives to SGD to mitigate these constraints. A hybrid PSO-SGD strategy is …

CLEVER: Stream-based Active Learning for Robust Semantic Perception from Human Instructions
Jongseok Lee, Timo Birr, Rudolph Triebel, Tamim Asfour
https://arxiv.org/abs/2507.15499

CLEVER: Stream-based Active Learning for Robust Semantic Perception from Human Instructions
We propose CLEVER, an active learning system for robust semantic perception with Deep Neural Networks (DNNs). For data arriving in streams, our system seeks human support when encountering failures and adapts DNNs online based on human instructions. In this way, CLEVER can eventually accomplish the given semantic perception tasks. Our main contribution is the design of a system that meets several desiderata of realizing the aforementioned capabilities. The key enabler herein is our Bayesian for…

Emergence of Functionally Differentiated Structures via Mutual Information Optimization in Recurrent Neural Networks
Yuki Tomoda, Ichiro Tsuda, Yutaka Yamaguti
https://arxiv.org/abs/2507.12858

Emergence of Functionally Differentiated Structures via Mutual Information Optimization in Recurrent Neural Networks
Functional differentiation in the brain emerges as distinct regions specialize and is key to understanding brain function as a complex system. Previous research has modeled this process using artificial neural networks with specific constraints. Here, we propose a novel approach that induces functional differentiation in recurrent neural networks by minimizing mutual information between neural subgroups via mutual information neural estimation. We apply our method to a 2-bit working memory task…

On Defining Neural Averaging
Su Hyeong Lee, Richard Ngo
https://arxiv.org/abs/2508.14832 https://arxiv.org/pdf/2508.14832

On Defining Neural Averaging
What does it even mean to average neural networks? We investigate the problem of synthesizing a single neural network from a collection of pretrained models, each trained on disjoint data shards, using only their final weights and no access to training data. In forming a definition of neural averaging, we take insight from model soup, which appears to aggregate multiple models into a singular model while enhancing generalization performance. In this work, we reinterpret model souping as a speci…

Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
Donghwa Kang, Doohyun Kim, Sang-Ki Ko, Jinkyu Lee, Hyeongboo Baek, Brent ByungHoon Kang
https://arxiv.org/abs/2508.13812

Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: substantial attack latency from multi-timestep processing, rendering them infeasible for practical real-time applications. This inefficiency stems from their design as direct extensions of ANN paradigms, which fail to exploit key SNN properties. In this paper, we propose the timestep-compressed attack (TCA), a novel fr…

Attention-Based Explainability for Structure-Property Relationships
Boris N. Slautin, Utkarsh Pratiush, Yongtao Liu, Hiroshi Funakubo, Vladimir V. Shvartsman, Doru C. Lupascu, Sergei V. Kalinin
https://arxiv.org/abs/2508.15493

Attention-Based Explainability for Structure-Property Relationships
Machine learning methods are emerging as a universal paradigm for constructing correlative structure-property relationships in materials science based on multimodal characterization. However, this necessitates development of methods for physical interpretability of the resulting correlative models. Here, we demonstrate the potential of attention-based neural networks for revealing structure-property relationships and the underlying physical mechanisms, using the ferroelectric properties of PbTi…

Robust Training with Data Augmentation for Medical Imaging Classification
Josu\'e Mart\'inez-Mart\'inez, Olivia Brown, Mostafa Karami, Sheida Nabavi
https://arxiv.org/abs/2506.17133

Robust Training with Data Augmentation for Medical Imaging Classification
Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect diagnostic reliability and undermine trust among healthcare professionals. In this study, we propose a robust training algorithm with data augmentation (RTDA) to mitigate these vulnerabilities in medical image classification. We benchmark classifier robustness a…

Neutrino Telescope Event Classification on Quantum Computers
Pablo Rodriguez-Grasa, Pavel Zhelnin, Carlos A. Arg\"uelles, Mikel Sanz
https://arxiv.org/abs/2506.16530

Neutrino Telescope Event Classification on Quantum Computers
Quantum computers represent a new computational paradigm with steadily improving hardware capabilities. In this article, we present the first study exploring how current quantum computers can be used to classify different neutrino event types observed in neutrino telescopes. We investigate two quantum machine learning approaches, Neural Projected Quantum Kernels (NPQKs) and Quantum Convolutional Neural Networks (QCNNs), and find that both achieve classification performance comparable to classic…

Hypergraph modelling of wave scattering to speed-up material design
Kunwoo Park, Ikbeom Lee, Seungmok Youn, Gitae Lee, Namkyoo Park, Sunkyu Yu
https://arxiv.org/abs/2507.15329

Hypergraph modelling of wave scattering to speed-up material design
Hypergraphs offer a generalized framework for understanding complex systems, covering group interactions of different orders beyond traditional pairwise interactions. This modelling allows for the simplified description of simultaneous interactions among multiple elements in coupled oscillators, graph neural networks, and entangled qubits. Here, we employ this generalized framework to describe wave-matter interactions for material design acceleration. By devising the set operations for multipar…

Lorentz-Equivariance without Limitations
Luigi Favaro, Gerrit Gerhartz, Fred A. Hamprecht, Peter Lippmann, Sebastian Pitz, Tilman Plehn, Huilin Qu, Jonas Spinner
https://arxiv.org/abs/2508.14898

Lorentz-Equivariance without Limitations
Lorentz Local Canonicalization (LLoCa) ensures exact Lorentz-equivariance for arbitrary neural networks with minimal computational overhead. For the LHC, it equivariantly predicts local reference frames for each particle and propagates any-order tensorial information between them. We apply it to graph networks and transformers. We showcase its cutting-edge performance on amplitude regression, end-to-end event generation, and jet tagging. For jet tagging, we introduce a large top tagging dataset…

Analyzing Internal Activity and Robustness of SNNs Across Neuron Parameter Space
Szymon Mazurek, Jakub Caputa, Maciej Wielgosz
https://arxiv.org/abs/2507.14757

Analyzing Internal Activity and Robustness of SNNs Across Neuron Parameter Space
Spiking Neural Networks (SNNs) offer energy-efficient and biologically plausible alternatives to traditional artificial neural networks, but their performance depends critically on the tuning of neuron model parameters. In this work, we identify and characterize an operational space - a constrained region in the neuron hyperparameter domain (specifically membrane time constant tau and voltage threshold vth) - within which the network exhibits meaningful activity and functional behavior. Operati…

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:

When Pipelined In-Memory Accelerators Meet Spiking Direct Feedback Alignment: A Co-Design for Neuromorphic Edge Computing
Haoxiong Ren, Yangu He, Kwunhang Wong, Rui Bao, Ning Lin, Zhongrui Wang, Dashan Shang
https://arxiv.org/abs/2507.15603

When Pipelined In-Memory Accelerators Meet Spiking Direct Feedback Alignment: A Co-Design for Neuromorphic Edge Computing
Spiking Neural Networks (SNNs) are increasingly favored for deployment on resource-constrained edge devices due to their energy-efficient and event-driven processing capabilities. However, training SNNs remains challenging because of the computational intensity of traditional backpropagation algorithms adapted for spike-based systems. In this paper, we propose a novel software-hardware co-design that introduces a hardware-friendly training algorithm, Spiking Direct Feedback Alignment (SDFA) and…

Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance
Shuchao Pang, Zhenghan Chen, Shen Zhang, Liming Lu, Siyuan Liang, Anan Du, Yongbin Zhou
https://arxiv.org/abs/2508.15650

Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance
Deep neural networks for 3D point clouds have been demonstrated to be vulnerable to adversarial examples. Previous 3D adversarial attack methods often exploit certain information about the target models, such as model parameters or outputs, to generate adversarial point clouds. However, in realistic scenarios, it is challenging to obtain any information about the target models under conditions of absolute security. Therefore, we focus on transfer-based attacks, where generating adversarial poin…

Classification of Histopathology Slides with Persistence Homology Convolutions
Shrunal Pothagoni, Benjamin Schweinhart
https://arxiv.org/abs/2507.14378 htt…

Classification of Histopathology Slides with Persistence Homology Convolutions
Convolutional neural networks (CNNs) are a standard tool for computer vision tasks such as image classification. However, typical model architectures may result in the loss of topological information. In specific domains such as histopathology, topology is an important descriptor that can be used to distinguish between disease-indicating tissue by analyzing the shape characteristics of cells. Current literature suggests that reintroducing topological information using persistent homology can im…

Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights
Krishnakumar Balasubramanian, Nathan Ross
https://arxiv.org/abs/2507.12686

Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights
We study the Finite-Dimensional Distributions (FDDs) of deep neural networks with randomly initialized weights that have finite-order moments. Specifically, we establish Gaussian approximation bounds in the Wasserstein-$1$ norm between the FDDs and their Gaussian limit assuming a Lipschitz activation function and allowing the layer widths to grow to infinity at arbitrary relative rates. In the special case where all widths are proportional to a common scale parameter $n$ and there are $L-1$ hid…

Replaced article(s) found for cs.NE. https://arxiv.org/list/cs.NE/new
[1/1]:
- Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
A. Martina Neuman, Dominik Dold, Philipp Christian Petersen

RCNet: $\Delta\Sigma$ IADCs as Recurrent AutoEncoders
Arnaud Verdant, William Guicquero, J\'er\^ome Chossat
https://arxiv.org/abs/2506.16903 https://…

RCNet: $ΔΣ$ IADCs as Recurrent AutoEncoders
This paper proposes a deep learning model (RCNet) for Delta-Sigma ($ΔΣ$) ADCs. Recurrent Neural Networks (RNNs) allow to describe both modulators and filters. This analogy is applied to Incremental ADCs (IADC). High-end optimizers combined with full-custom losses are used to define additional hardware design constraints: quantized weights, signal saturation, temporal noise injection, devices area. Focusing on DC conversion, our early results demonstrate that $SNR$ defined as an Effective Numb…

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…

Solving nonconvex Hamilton--Jacobi--Isaacs equations with PINN-based policy iteration
Hee Jun Yang, Min Jung Kim, Yeoneung Kim
https://arxiv.org/abs/2507.15455

Solving nonconvex Hamilton--Jacobi--Isaacs equations with PINN-based policy iteration
We propose a mesh-free policy iteration framework that combines classical dynamic programming with physics-informed neural networks (PINNs) to solve high-dimensional, nonconvex Hamilton--Jacobi--Isaacs (HJI) equations arising in stochastic differential games and robust control. The method alternates between solving linear second-order PDEs under fixed feedback policies and updating the controls via pointwise minimax optimization using automatic differentiation. Under standard Lipschitz and unif…

Pixel-wise Modulated Dice Loss for Medical Image Segmentation
Seyed Mohsen Hosseini
https://arxiv.org/abs/2506.15744 https://arxiv.or…

Pixel-wise Modulated Dice Loss for Medical Image Segmentation
Class imbalance and the difficulty imbalance are the two types of data imbalance that affect the performance of neural networks in medical segmentation tasks. In class imbalance the loss is dominated by the majority classes and in difficulty imbalance the loss is dominated by easy to classify pixels. This leads to an ineffective training. Dice loss, which is based on a geometrical metric, is very effective in addressing the class imbalance compared to the cross entropy (CE) loss, which is adopt…

GDNSQ: Gradual Differentiable Noise Scale Quantization for Low-bit Neural Networks
Sergey Salishev, Ian Akhremchik
https://arxiv.org/abs/2508.14004 https://

GDNSQ: Gradual Differentiable Noise Scale Quantization for Low-bit Neural Networks
Quantized neural networks can be viewed as a chain of noisy channels, where rounding in each layer reduces capacity as bit-width shrinks; the floating-point (FP) checkpoint sets the maximum input rate. We track capacity dynamics as the average bit-width decreases and identify resulting quantization bottlenecks by casting fine-tuning as a smooth, constrained optimization problem. Our approach employs a fully differentiable Straight-Through Estimator (STE) with learnable bit-width, noise scale an…

Crosslisted article(s) found for cs.AR. https://arxiv.org/list/cs.AR/new
[1/1]:
- Quantized Neural Networks for Microcontrollers: A Comprehensive Review of Methods, Platforms, and...
Hamza A. Abushahla, Dara Varam, Ariel J. N. Panopio, Mohamed I. AlHajri

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:

Neural Architecture Search with Mixed Bio-inspired Learning Rules
Imane Hamzaoui, Riyadh Baghdadi
https://arxiv.org/abs/2507.13485 https://

Neural Architecture Search with Mixed Bio-inspired Learning Rules
Bio-inspired neural networks are attractive for their adversarial robustness, energy frugality, and closer alignment with cortical physiology, yet they often lag behind back-propagation (BP) based models in accuracy and ability to scale. We show that allowing the use of different bio-inspired learning rules in different layers, discovered automatically by a tailored neural-architecture-search (NAS) procedure, bridges this gap. Starting from standard NAS baselines, we enlarge the search space to…

Brain Stroke Classification Using Wavelet Transform and MLP Neural Networks on DWI MRI Images
Mana Mohammadi, Amirhesam Jafari Rad, Ashkan Behrouzi
https://arxiv.org/abs/2506.15364

Brain Stroke Classification Using Wavelet Transform and MLP Neural Networks on DWI MRI Images
This paper presents a lightweight framework for classifying brain stroke types from Diffusion-Weighted Imaging (DWI) MRI scans, employing a Multi-Layer Perceptron (MLP) neural network with Wavelet Transform for feature extraction. Accurate and timely stroke detection is critical for effective treatment and improved patient outcomes in neuroimaging. While Convolutional Neural Networks (CNNs) are widely used for medical image analysis, their computational complexity often hinders deployment in re…

Reduced-order modeling of Hamiltonian dynamics based on symplectic neural networks
Yongsheng Chen, Wei Guo, Qi Tang, Xinghui Zhong
https://arxiv.org/abs/2508.11911 https://

Reduced-order modeling of Hamiltonian dynamics based on symplectic neural networks
We introduce a novel data-driven symplectic induced-order modeling (ROM) framework for high-dimensional Hamiltonian systems that unifies latent-space discovery and dynamics learning within a single, end-to-end neural architecture. The encoder-decoder is built from Henon neural networks (HenonNets) and may be augmented with linear SGS-reflector layers. This yields an exact symplectic map between full and latent phase spaces. Latent dynamics are advanced by a symplectic flow map implemented as a …

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/9]:
- Eau De $Q$-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning
Th\'eo Vincent, Tim Faust, Yogesh Tripathi, Jan Peters, Carlo D'Eramo

Replaced article(s) found for cs.NE. https://arxiv.org/list/cs.NE/new
[1/1]:
- Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimony
James Bagrow, Josh Bongard

Distributed Detection of Adversarial Attacks in Multi-Agent Reinforcement Learning with Continuous Action Space
Kiarash Kazari, Ezzeldin Shereen, Gy\"orgy D\'an
https://arxiv.org/abs/2508.15764

Distributed Detection of Adversarial Attacks in Multi-Agent Reinforcement Learning with Continuous Action Space
We address the problem of detecting adversarial attacks against cooperative multi-agent reinforcement learning with continuous action space. We propose a decentralized detector that relies solely on the local observations of the agents and makes use of a statistical characterization of the normal behavior of observable agents. The proposed detector utilizes deep neural networks to approximate the normal behavior of agents as parametric multivariate Gaussian distributions. Based on the predicted…

Deep Unfolding Network for Nonlinear Multi-Frequency Electrical Impedance Tomography
Giovanni S. Alberti, Damiana Lazzaro, Serena Morigi, Luca Ratti, Matteo Santacesaria
https://arxiv.org/abs/2507.16678

Deep Unfolding Network for Nonlinear Multi-Frequency Electrical Impedance Tomography
Multi-frequency Electrical Impedance Tomography (mfEIT) represents a promising biomedical imaging modality that enables the estimation of tissue conductivities across a range of frequencies. Addressing this challenge, we present a novel variational network, a model-based learning paradigm that strategically merges the advantages and interpretability of classical iterative reconstruction with the power of deep learning. This approach integrates graph neural networks (GNNs) within the iterative P…

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…

Special Session: Sustainable Deployment of Deep Neural Networks on Non-Volatile Compute-in-Memory Accelerators
Yifan Qin, Zheyu Yan, Wujie Wen, Xiaobo Sharon Hu, Yiyu Shi
https://arxiv.org/abs/2508.12195

Special Session: Sustainable Deployment of Deep Neural Networks on Non-Volatile Compute-in-Memory Accelerators
Non-volatile memory (NVM) based compute-in-memory (CIM) accelerators have emerged as a sustainable solution to significantly boost energy efficiency and minimize latency for Deep Neural Networks (DNNs) inference due to their in-situ data processing capabilities. However, the performance of NVCIM accelerators degrades because of the stochastic nature and intrinsic variations of NVM devices. Conventional write-verify operations, which enhance inference accuracy through iterative writing and verif…

Text2Weight: Bridging Natural Language and Neural Network Weight Spaces
Bowen Tian, Wenshuo Chen, Zexi Li, Songning Lai, Jiemin Wu, Yutao Yue
https://arxiv.org/abs/2508.13633 ht…

Text2Weight: Bridging Natural Language and Neural Network Weight Spaces
How far are we really from automatically generating neural networks? While neural network weight generation shows promise, current approaches struggle with generalization to unseen tasks and practical application exploration. To address this, we propose T2W, a diffusion transformer framework that generates task-specific weights conditioned on natural language descriptions. T2W hierarchically processes network parameters into uniform blocks, integrates text embeddings from CLIP via a prior atten…

Multi-Plasticity Synergy with Adaptive Mechanism Assignment for Training Spiking Neural Networks
Yuzhe Liu, Xin Deng, Qiang Yu
https://arxiv.org/abs/2508.13673 https://

Multi-Plasticity Synergy with Adaptive Mechanism Assignment for Training Spiking Neural Networks
Spiking Neural Networks (SNNs) are promising brain-inspired models known for low power consumption and superior potential for temporal processing, but identifying suitable learning mechanisms remains a challenge. Despite the presence of multiple coexisting learning strategies in the brain, current SNN training methods typically rely on a single form of synaptic plasticity, which limits their adaptability and representational capability. In this paper, we propose a biologically inspired training…

Evolving Neural Controllers for Xpilot-AI Racing Using Neuroevolution of Augmenting Topologies
Jim O'Connor, Nicholas Lorentzen, Gary B. Parker, Derin Gezgin
https://arxiv.org/abs/2507.13549

Evolving Neural Controllers for Xpilot-AI Racing Using Neuroevolution of Augmenting Topologies
This paper investigates the development of high-performance racing controllers for a newly implemented racing mode within the Xpilot-AI platform, utilizing the Neuro Evolution of Augmenting Topologies (NEAT) algorithm. By leveraging NEAT's capability to evolve both the structure and weights of neural networks, we develop adaptive controllers that can navigate complex circuits under the challenging space simulation physics of Xpilot-AI, which includes elements such as inertia, friction, and grav…

Robust Convolution Neural ODEs via Contractivity-promoting regularization
Muhammad Zakwan, Liang Xu, Giancarlo Ferrari-Trecate
https://arxiv.org/abs/2508.11432 https://

Robust Convolution Neural ODEs via Contractivity-promoting regularization
Neural networks can be fragile to input noise and adversarial attacks. In this work, we consider Convolutional Neural Ordinary Differential Equations (NODEs), a family of continuous-depth neural networks represented by dynamical systems, and propose to use contraction theory to improve their robustness. For a contractive dynamical system two trajectories starting from different initial conditions converge to each other exponentially fast. Contractive Convolutional NODEs can enjoy increase…

A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
Qingyan Meng, Mingqing Xiao, Zhengyu Ma, Huihui Zhou, Yonghong Tian, Zhouchen Lin
https://arxiv.org/abs/2508.12609

A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
Spiking Neural Networks (SNNs) are a promising approach to low-power applications on neuromorphic hardware due to their energy efficiency. However, training SNNs is challenging because of the non-differentiable spike generation function. To address this issue, the commonly used approach is to adopt the backpropagation through time framework, while assigning the gradient of the non-differentiable function with some surrogates. Similarly, Binary Neural Networks (BNNs) also face the non-differenti…

Quantization Meets Spikes: Lossless Conversion in the First Timestep via Polarity Multi-Spike Mapping
Hangming Zhang, Zheng Li, Qiang Yu
https://arxiv.org/abs/2508.14520 https:/…

Quantization Meets Spikes: Lossless Conversion in the First Timestep via Polarity Multi-Spike Mapping
Spiking neural networks (SNNs) offer advantages in computational efficiency via event-driven computing, compared to traditional artificial neural networks (ANNs). While direct training methods tackle the challenge of non-differentiable activation mechanisms in SNNs, they often suffer from high computational and energy costs during training. As a result, ANN-to-SNN conversion approach still remains a valuable and practical alternative. These conversion-based methods aim to leverage the discrete …

Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
Fanzhen Liu, Xiaoxiao Ma, Jian Yang, Alsharif Abuadbba, Kristen Moore, Surya Nepal, Cecile Paris, Quan Z. Sheng, Jia Wu
https://arxiv.org/abs/2508.11513

Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
Enhancing the interpretability of graph neural networks (GNNs) is crucial to ensure their safe and fair deployment. Recent work has introduced self-explainable GNNs that generate explanations as part of training, improving both faithfulness and efficiency. Some of these models, such as ProtGNN and PGIB, learn class-specific prototypes, offering a potential pathway toward class-level explanations. However, their evaluations focus solely on instance-level explanations, leaving open the question o…

Targeted Deep Architectures: A TMLE-Based Framework for Robust Causal Inference in Neural Networks
Yi Li, David Mccoy, Nolan Gunter, Kaitlyn Lee, Alejandro Schuler, Mark van der Laan
https://arxiv.org/abs/2507.12435

Targeted Deep Architectures: A TMLE-Based Framework for Robust Causal Inference in Neural Networks
Modern deep neural networks are powerful predictive tools yet often lack valid inference for causal parameters, such as treatment effects or entire survival curves. While frameworks like Double Machine Learning (DML) and Targeted Maximum Likelihood Estimation (TMLE) can debias machine-learning fits, existing neural implementations either rely on "targeted losses" that do not guarantee solving the efficient influence function equation or computationally expensive post-hoc "fluctuations" for mult…

Encoding Optimization for Low-Complexity Spiking Neural Network Equalizers in IM/DD Systems
Eike-Manuel Edelmann, Alexander von Bank, Laurent Schmalen
https://arxiv.org/abs/2508.13783

Encoding Optimization for Low-Complexity Spiking Neural Network Equalizers in IM/DD Systems
Neural encoding parameters for spiking neural networks (SNNs) are typically set heuristically. We propose a reinforcement learning-based algorithm to optimize them. Applied to an SNN-based equalizer and demapper in an IM/DD system, the method improves performance while reducing computational load and network size.

Replaced article(s) found for cs.NE. https://arxiv.org/list/cs.NE/new
[1/1]:
- Reinitializing weights vs units for maintaining plasticity in neural networks
J. Fernando Hernandez-Garcia, Shibhansh Dohare, Jun Luo, Rich S. Sutton

Finite-Width Neural Tangent Kernels from Feynman Diagrams
Max Guillen, Philipp Misof, Jan E. Gerken
https://arxiv.org/abs/2508.11522 https://arxiv.org/pdf/…

Finite-Width Neural Tangent Kernels from Feynman Diagrams
Neural tangent kernels (NTKs) are a powerful tool for analyzing deep, non-linear neural networks. In the infinite-width limit, NTKs can easily be computed for most common architectures, yielding full analytic control over the training dynamics. However, at infinite width, important properties of training such as NTK evolution or feature learning are absent. Nevertheless, finite width effects can be included by computing corrections to the Gaussian statistics at infinite width. We introduce Feyn…

Online Training and Pruning of Deep Reinforcement Learning Networks
Valentin Frank Ingmar Guenter, Athanasios Sideris
https://arxiv.org/abs/2507.11975 http…

Online Training and Pruning of Deep Reinforcement Learning Networks
Scaling deep neural networks (NN) of reinforcement learning (RL) algorithms has been shown to enhance performance when feature extraction networks are used but the gained performance comes at the significant expense of increased computational and memory complexity. Neural network pruning methods have successfully addressed this challenge in supervised learning. However, their application to RL is underexplored. We propose an approach to integrate simultaneous training and pruning within advance…