Tootfinder

Last week, we continued our #ISE2025 lecture on distributional semantics with the introduction of neural language models (NLMs) and compared them to traditional statistical n-gram models.
Benefits of NLMs:
- Capturing Long-Range Dependencies
- Computational and Statistical Tractability
- Improved Generalisation
- Higher Accuracy
@…

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…

Real-World Modeling of Computation Offloading for Neural Networks with Early Exits and Splits
Jan Danek, Zdenek Becvar, Adam Janes
https://arxiv.org/abs/2505.22149

Real-World Modeling of Computation Offloading for Neural Networks with Early Exits and Splits
We focus on computation offloading of applications based on convolutional neural network (CNN) from moving devices, such as mobile robots or autonomous vehicles, to MultiAccess Edge Computing (MEC) servers via a mobile network. In order to reduce overall CNN inference time, we design and implement CNN with early exits and splits, allowing a flexible partial or full offloading of CNN inference. Through real-world experiments, we analyze an impact of the CNN inference offloading on the total CNN …

Organizational Regularities in Recurrent Neural Networks
Claus Metzner, Achim Schilling, Andreas Maier, Patrick Krauss
https://arxiv.org/abs/2505.22047 htt…

Organizational Regularities in Recurrent Neural Networks
Previous work has shown that the dynamical regime of Recurrent Neural Networks (RNNs) - ranging from oscillatory to chaotic and fixpoint behavior - can be controlled by the global distribution of weights in connection matrices with statistically independent elements. However, it remains unclear how network dynamics respond to organizational regularities in the weight matrix, as often observed in biological neural networks. Here, we investigate three such regularities: (1) monopolar output weigh…

IMC-PINN-FE: A Physics-Informed Neural Network for Patient-Specific Left Ventricular Finite Element Modeling with Image Motion Consistency and Biomechanical Parameter Estimation
Siyu Mu, Wei Xuan Chan, Choon Hwai Yap
https://arxiv.org/abs/2506.20696

IMC-PINN-FE: A Physics-Informed Neural Network for Patient-Specific Left Ventricular Finite Element Modeling with Image Motion Consistency and Biomechanical Parameter Estimation
Elucidating the biomechanical behavior of the myocardium is crucial for understanding cardiac physiology, but cannot be directly inferred from clinical imaging and typically requires finite element (FE) simulations. However, conventional FE methods are computationally expensive and often fail to reproduce observed cardiac motions. We propose IMC-PINN-FE, a physics-informed neural network (PINN) framework that integrates imaged motion consistency (IMC) with FE modeling for patient-specific left …

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

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

Constructive community race: full-density spiking neural network model drives neuromorphic computing
Johanna Senk, Anno Kurth, Steve Furber, Tobias Gemmeke, Bruno Golosio, Arne Heittmann, James C. Knight, Eric M\"uller, Tobias Noll, Thomas Nowotny, Gorka Peraza Coppola, Luca Peres, Oliver Rhodes, Andrew Rowley, Johannes Schemmel, Tim Stadtmann, Tom Tetzlaff, Gianmarco Tiddia, Sacha J. van Albada, Jos\'e Villamar, Markus Diesmann

Constructive community race: full-density spiking neural network model drives neuromorphic computing
The local circuitry of the mammalian brain is a focus of the search for generic computational principles because it is largely conserved across species and modalities. In 2014 a model was proposed representing all neurons and synapses of the stereotypical cortical microcircuit below $1\,\text{mm}^2$ of brain surface. The model reproduces fundamental features of brain activity but its impact remained limited because of its computational demands. For theory and simulation, however, the model was …

This https://arxiv.org/abs/2412.18872 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Proton Flux Measurement from Neutron Monitor Data Using Neural Networks
Accurate measurements of cosmic ray proton flux are essential for studying the modulation processes of cosmic rays during the solar activity cycle. A proton flux measurement method, based on ground-based neutron monitor (NM) data and deep learning techniques, is presented. After the necessary pre-processing of ground-based NM data using a convolutional neural network (CNN) model, we simulate the relationship between NM observations and proton flux measured by the Alpha Magnetic Spectrometer (AM…

Generating and Customizing Robotic Arm Trajectories using Neural Networks
Andrej L\'u\v{c}ny, Matilde Antonj, Carlo Mazzola, Hana Horn\'a\v{c}kov\'a, Igor Farka\v{s}
https://arxiv.org/abs/2506.20259

Generating and Customizing Robotic Arm Trajectories using Neural Networks
We introduce a neural network approach for generating and customizing the trajectory of a robotic arm, that guarantees precision and repeatability. To highlight the potential of this novel method, we describe the design and implementation of the technique and show its application in an experimental setting of cognitive robotics. In this scenario, the NICO robot was characterized by the ability to point to specific points in space with precise linear movements, increasing the predictability of t…

Poster: Enhancing GNN Robustness for Network Intrusion Detection via Agent-based Analysis
Zhonghao Zhan, Huichi Zhou, Hamed Haddadi
https://arxiv.org/abs/2506.20806

Poster: Enhancing GNN Robustness for Network Intrusion Detection via Agent-based Analysis
Graph Neural Networks (GNNs) show great promise for Network Intrusion Detection Systems (NIDS), particularly in IoT environments, but suffer performance degradation due to distribution drift and lack robustness against realistic adversarial attacks. Current robustness evaluations often rely on unrealistic synthetic perturbations and lack demonstrations on systematic analysis of different kinds of adversarial attack, which encompass both black-box and white-box scenarios. This work proposes a no…

Practical insights on the effect of different encodings, ans\"atze and measurements in quantum and hybrid convolutional neural networks
Jes\'us Lozano-Cruz, Albert Nieto-Morales, Oriol Ball\'o-Gimbernat, Adan Garriga, Ant\'on Rodr\'iguez-Otero, Alejandro Borrallo-Rentero
https://arxiv.org/abs/2506.20355

Practical insights on the effect of different encodings, ansätze and measurements in quantum and hybrid convolutional neural networks
This study investigates the design choices of parameterized quantum circuits (PQCs) within quantum and hybrid convolutional neural network (HQNN and QCNN) architectures, applied to the task of satellite image classification using the EuroSAT dataset. We systematically evaluate the performance implications of data encoding techniques, variational ansätze, and measurement in approx. 500 distinct model configurations. Our analysis reveals a clear hierarchy of influence on model performance. For h…

KKT-based optimality conditions for neural network approximation
Vinesha Peiris, Nadezda Sukhorukova, Julien Ugon
https://arxiv.org/abs/2506.17305 https://…

KKT-based optimality conditions for neural network approximation
In this paper, we obtain necessary optimality conditions for neural network approximation. We consider neural networks in Manhattan ($l_1$ norm) and Chebyshev ($\max$ norm). The optimality conditions are based on neural networks with at most one hidden layer. We reformulate nonsmooth unconstrained optimisation problems as larger dimension constrained problems with smooth objective functions and constraints. Then we use KKT conditions to develop the necessary conditions and present the optimalit…

Joint Quantization and Pruning Neural Networks Approach: A Case Study on FSO Receivers
Mohanad Obeed, Ming Jian
https://arxiv.org/abs/2506.20084 https://…

Joint Quantization and Pruning Neural Networks Approach: A Case Study on FSO Receivers
Towards fast, hardware-efficient, and low-complexity receivers, we propose a compression-aware learning approach and examine it on free-space optical (FSO) receivers for turbulence mitigation. The learning approach jointly quantize, prune, and train a convolutional neural network (CNN). In addition, we propose to have the CNN weights of power of two values so we replace the multiplication operations bit-shifting operations in every layer that has significant lower computational cost. The compre…

This https://arxiv.org/abs/2505.09551 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

Fast Learning in Quantitative Finance with Extreme Learning Machine
This paper demonstrates that a broad class of problems in quantitative finance, including those previously addressed using deep neural networks, can be efficiently solved using single-layer neural networks without iterative gradient-based training, namely extreme learning machine (ELM). ELM utilizes a single-layer network with randomly initialized hidden nodes and analytically computed output weights obtained via convex optimization, enabling rapid training and inference. Both supervised and un…

Neural Functionally Generated Portfolios
Michael Monoyios, Olivia Pricilia
https://arxiv.org/abs/2506.19715 https://arxiv.org/pdf/250…

Neural Functionally Generated Portfolios
We introduce a novel neural-network-based approach to learning the generating function $G(\cdot)$ of a functionally generated portfolio (FGP) from synthetic or real market data. In the neural network setting, the generating function is represented as $G_θ(\cdot)$, where $θ$ is an iterable neural network parameter vector, and $G_θ(\cdot)$ is trained to maximise investment return relative to the market portfolio. We compare the performance of the Neural FGP approach against classical FGP bench…

Recurrent neural network-based robust control systems with closed-loop regional incremental ISS and application to MPC design
Daniele Ravasio, Marcello Farina, Alessio La Bella, Andrea Ballarino
https://arxiv.org/abs/2506.20334

Recurrent neural network-based robust control systems with closed-loop regional incremental ISS and application to MPC design
This paper investigates the design of output-feedback schemes for systems described by a class of recurrent neural networks. We propose a procedure based on linear matrix inequalities for designing an observer and a static state-feedback controller. The algorithm leverages global and regional incremental input-to-state stability (incremental ISS) and enables the tracking of constant setpoints, ensuring robustness to disturbances and state estimation uncertainty. To address the potential limitat…

SHAMaNS: Sound Localization with Hybrid Alpha-Stable Spatial Measure and Neural Steerer
Diego Di Carlo (RIKEN AIP), Mathieu Fontaine (LTCI, IP Paris), Aditya Arie Nugraha (RIKEN AIP), Yoshiaki Bando (RIKEN AIP), Kazuyoshi Yoshii
https://arxiv.org/abs/2506.18954

SHAMaNS: Sound Localization with Hybrid Alpha-Stable Spatial Measure and Neural Steerer
This paper describes a sound source localization (SSL) technique that combines an $α$-stable model for the observed signal with a neural network-based approach for modeling steering vectors. Specifically, a physics-informed neural network, referred to as Neural Steerer, is used to interpolate measured steering vectors (SVs) on a fixed microphone array. This allows for a more robust estimation of the so-called $α$-stable spatial measure, which represents the most plausible direction of arrival…

New pre-print! #ai
**Universal pre-training by iterated random computation.**
⌨️🐒 A monkey behind a typewriter will produce the collected works of Shakespeare eventually.
💻🐒 But what if we put a monkey behind a computer?
⌨️🐒 needs to be lucky enough to type all characters of all of Shakespeare correctly. 💻🐒 only needs to be lucky enough to type a program for Shakespeare.

Universal pre-training by iterated random computation
We investigate the use of randomly generated data for the sake of pre-training a model. We justify this approach theoretically from the perspective of algorithmic complexity, building on recent research that shows that sequence models can be trained to approximate Solomonoff induction. We derive similar, but complementary theoretical results. We show empirically that synthetically generated data can be used to pre-train a model before the data is seen. We replicate earlier results that models t…

SparseDPD: A Sparse Neural Network-based Digital Predistortion FPGA Accelerator for RF Power Amplifier Linearization
Manno Versluis, Yizhuo Wu, Chang Gao
https://arxiv.org/abs/2506.16591

SparseDPD: A Sparse Neural Network-based Digital Predistortion FPGA Accelerator for RF Power Amplifier Linearization
Digital predistortion (DPD) is crucial for linearizing radio frequency (RF) power amplifiers (PAs), improving signal integrity and efficiency in wireless systems. Neural network (NN)-based DPD methods surpass traditional polynomial models but face computational challenges limiting their practical deployment. This paper introduces SparseDPD, an FPGA accelerator employing a spatially sparse phase-normalized time-delay neural network (PNTDNN), optimized through unstructured pruning to reduce compu…

Confusion-driven machine learning of structural phases of a flexible, magnetic Stockmayer polymer
Dilina Perera, Samuel McAllister, Joan Josep Cerd\`a, Thomas Vogel
https://arxiv.org/abs/2506.20899

Confusion-driven machine learning of structural phases of a flexible, magnetic Stockmayer polymer
We use a semi-supervised, neural-network based machine learning technique, the confusion method, to investigate structural transitions in magnetic polymers, which we model as chains of magnetic colloidal nanoparticles characterized by dipole-dipole and Lennard-Jones interactions. As input for the neural network we use the particle positions and magnetic dipole moments of equilibrium polymer configurations, which we generate via replica-exchange Wang--Landau simulations. We demonstrate that by m…

Structural System Identification via Validation and Adaptation
Cristian L\'opez, Keegan J. Moore
https://arxiv.org/abs/2506.20799 https://

Structural System Identification via Validation and Adaptation
Estimating the governing equation parameter values is essential for integrating experimental data with scientific theory to understand, validate, and predict the dynamics of complex systems. In this work, we propose a new method for structural system identification (SI), uncertainty quantification, and validation directly from data. Inspired by generative modeling frameworks, a neural network maps random noise to physically meaningful parameters. These parameters are then used in the known equa…

Comparative analysis of financial data differentiation techniques using LSTM neural network
Dominik Stempie\'n, Janusz Gajda
https://arxiv.org/abs/2505.19243

Comparative analysis of financial data differentiation techniques using LSTM neural network
We compare traditional approach of computing logarithmic returns with the fractional differencing method and its tempered extension as methods of data preparation before their usage in advanced machine learning models. Differencing parameters are estimated using multiple techniques. The empirical investigation is conducted on data from four major stock indices covering the most recent 10-year period. The set of explanatory variables is additionally extended with technical indicators. The effect…

A Physics-Informed Neural Network Framework for Simulating Creep Buckling in Growing Viscoelastic Biological Tissues
Zhongya Lin, Jinshuai Bai, Shuang Li, Xindong Chen, Bo Li, Xi-Qiao Feng
https://arxiv.org/abs/2506.18565

A Physics-Informed Neural Network Framework for Simulating Creep Buckling in Growing Viscoelastic Biological Tissues
Modeling viscoelastic behavior is crucial in engineering and biomechanics, where materials undergo time-dependent deformations, including stress relaxation, creep buckling and biological tissue development. Traditional numerical methods, like the finite element method, often require explicit meshing, artificial perturbations or embedding customised programs to capture these phenomena, adding computational complexity. In this study, we develop an energy-based physics-informed neural network (PIN…

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

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

Rank Inspired Neural Network for solving linear partial differential equations
Wentao Peng, Yunqing Huang, Nianyu Yi
https://arxiv.org/abs/2506.17654 https…

Rank Inspired Neural Network for solving linear partial differential equations
This paper proposes a rank inspired neural network (RINN) to tackle the initialization sensitivity issue of physics informed extreme learning machines (PIELM) when numerically solving partial differential equations (PDEs). Unlike PIELM which randomly initializes the parameters of its hidden layers, RINN incorporates a preconditioning stage. In this stage, covariance-driven regularization is employed to optimize the orthogonality of the basis functions generated by the last hidden layer. The key…

Learning-Based Distance Estimation for 360{\deg} Single-Sensor Setups
Yitong Quan, Benjamin Kiefer, Martin Messmer, Andreas Zell
https://arxiv.org/abs/2506.20586

Learning-Based Distance Estimation for 360° Single-Sensor Setups
Accurate distance estimation is a fundamental challenge in robotic perception, particularly in omnidirectional imaging, where traditional geometric methods struggle with lens distortions and environmental variability. In this work, we propose a neural network-based approach for monocular distance estimation using a single 360° fisheye lens camera. Unlike classical trigonometric techniques that rely on precise lens calibration, our method directly learns and infers the distance of objects from …

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

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

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…

Optimizing SPION Labeling for Single-Cell Magnetic Microscopy
A. Pointner, D. Thalheim, S. Belasi, L. Heinen, C. Bonato, T. Luehmann, J. Meijer, R. Tietze, C. Alexiou, R. Schneider-Stock, R. Nagy
https://arxiv.org/abs/2505.20373

Optimizing SPION Labeling for Single-Cell Magnetic Microscopy
This study explores the correlation between iron mass on cell surfaces and the resultant magnetic field. Human colorectal cancer cells (HT29 line) were labeled with varying concentrations of SPIONs and imaged via a NV center widefield magnetic microscope. To assess the labeling efficacy, a convolutional neural network trained on simulated magnetic dipole data was utilized to reconstruct key labeling parameters on a cell-by-cell basis, including cell diameter, sensor proximity, and the iron mass…

Replaced article(s) found for cs.ET. https://arxiv.org/list/cs.ET/new
[1/1]:
- A Scalable Quantum Neural Network for Approximate SRBB-Based Unitary Synthesis
Giacomo Belli, Marco Mordacci, Michele Amoretti

DualEquiNet: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules
Junjie Xu, Jiahao Zhang, Mangal Prakash, Xiang Zhang, Suhang Wang
https://arxiv.org/abs/2506.19862

DualEquiNet: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules
Geometric graph neural networks (GNNs) that respect E(3) symmetries have achieved strong performance on small molecule modeling, but they face scalability and expressiveness challenges when applied to large biomolecules such as RNA and proteins. These systems require models that can simultaneously capture fine-grained atomic interactions, long-range dependencies across spatially distant components, and biologically relevant hierarchical structure, such as atoms forming residues, which in turn f…

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

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

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…

Generalised Time-Series Analysis of Fault Mechanics Using Explainable AI
Thomas King, Sergio Vinciguerra
https://arxiv.org/abs/2505.21312 https://

Generalised Time-Series Analysis of Fault Mechanics Using Explainable AI
Understanding how faults nucleate and grow is a critical problem in earthquake science and hazard assessment. This study examines fault development in Alzo granite under triaxial pressures ranging from 5 to 40 MPa by applying a Time Delay Neural Network (TDNN) to multi-parameter acoustic emission (AE) data. The TDNN integrates waveform-derived attributes, including peak delay and scattering attenuation, with occurrence-based metrics such as time distributions, Gutenberg-Richter b-values, and sp…

Replaced article(s) found for physics.data-an. https://arxiv.org/list/physics.data-an/new
[1/1]:
- Graph Neural Network for Neutrino Physics Event Reconstruction
Hewes, Aurisano, Cerati, Kowalkowski, Lee, Liao, Grzenda, Gumpula, Zhang

Signatures of planets and Galactic subpopulations in solar analogs. Precise chemical abundances with neural networks
Giulia Martos, Jorge Mel\'endez, Lorenzo Spina, Sara Lucatello
https://arxiv.org/abs/2506.20345

Signatures of planets and Galactic subpopulations in solar analogs. Precise chemical abundances with neural networks
The aim of this work is to obtain precise atmospheric parameters and chemical abundances automatically for solar twins and analogs to find signatures of exoplanets, as well as to assess how peculiar the Sun is compared to these stars and to analyze any possible fine structures in the Galactic thin disk. We developed a neural network (NN) algorithm using Python to obtain these parameters for a sample of 99 solar twins and solar analogs previously studied in the literature from normalized high-qu…

A Simple but Accurate Approximation for Multivariate Gaussian Rate-Distortion Function and Its Application in Maximal Coding Rate Reduction
Zhenglin Huang, Qifa Yan, Bin Dai, Xiaohu Tang
https://arxiv.org/abs/2506.18613

A Simple but Accurate Approximation for Multivariate Gaussian Rate-Distortion Function and Its Application in Maximal Coding Rate Reduction
The multivariate Gaussian rate-distortion (RD) function is crucial in various applications, such as digital communications, data storage, or neural networks. However, the complex form of the multivariate Gaussian RD function prevents its application in many neural network-based scenarios that rely on its analytical properties, for example, white-box neural networks, multi-device task-oriented communication, and semantic communication. This paper proposes a simple but accurate approximation for …

A Neural-Operator Surrogate for Platelet Deformation Across Capillary Numbers
Marco Laudato
https://arxiv.org/abs/2506.20341 https://…

A Neural-Operator Surrogate for Platelet Deformation Across Capillary Numbers
Reliable multiscale models of thrombosis require platelet-scale fidelity at organ-scale cost, a gap that scientific machine learning has the potential to narrow. We train a DeepONet surrogate on platelet dynamics generated with LAMMPS for platelets spanning ten elastic moduli and capillary numbers (0.07 - 0.77). The network takes in input the wall shear stress, bond stiffness, time, and initial particle coordinates and returns the full three-dimensional deformation of the membrane. Mean-squared…

Learning Heat Transport Kernels Using a Nonlocal Heat Transport Theory-Informed Neural Network
Mufei Luo, Charles Heaton, Yizhen Wang, Daniel Plummer, Mila Fitzgerald, Francesco Miniati, Sam M. Vinko, Gianluca Gregori
https://arxiv.org/abs/2506.16619

Learning Heat Transport Kernels Using a Nonlocal Heat Transport Theory-Informed Neural Network
We present a data-driven framework for the modeling of nonlocal heat transport in plasmas using a nonlocal theory informed neural network trained on kinetic Particle-in-Cell simulations that span both local and nonlocal regimes. The model learns spatiotemporal heat flux kernels directly from simulation data, capturing dynamic transport behaviors beyond the reach of classical formulations. Unlike time-independent kernel models such as Luciani Mora Virmont and Schurtz Nicolaï Busquet models, our…

Replaced article(s) found for cs.LO. https://arxiv.org/list/cs.LO/new
[1/1]:
- A Certified Proof Checker for Deep Neural Network Verification in Imandra
Remi Desmartin, Omri Isac, Grant Passmore, Ekaterina Komendantskaya, Kathrin Stark, Guy Katz

Testing a 95 GeV Scalar at the CEPC with Machine Learning
Yabo Dong, Manqi Ruan, Kun Wang, Haijun Yang, Jingya Zhu
https://arxiv.org/abs/2506.21454 https:/…

Testing a 95 GeV Scalar at the CEPC with Machine Learning
Several possible excesses around $95\,$GeV hint at an additional light scalar beyond the Standard Model. We examine the capability of the CEPC to test this hypothesis in the Higgsstrahlung channel $e^{+}e^{-}\!\to ZS$ with $Z\!\toμ^{+}μ^{-}$ and $S\!\toτ^{+}τ^{-}$. Full detector simulation shows that the optimal center-of-mass energy to study the 95 GeV light scalar is 210 GeV. A deep neural network classifier reduces the luminosity required for discovery by half. At $L=500$ fb$^{-1}$, the …

Robust Anomaly Detection in Network Traffic: Evaluating Machine Learning Models on CICIDS2017
Zhaoyang Xu, Yunbo Liu
https://arxiv.org/abs/2506.19877 https…

Robust Anomaly Detection in Network Traffic: Evaluating Machine Learning Models on CICIDS2017
Identifying suitable machine learning paradigms for intrusion detection remains critical for building effective and generalizable security solutions. In this study, we present a controlled comparison of four representative models - Multi-Layer Perceptron (MLP), 1D Convolutional Neural Network (CNN), One-Class Support Vector Machine (OCSVM) and Local Outlier Factor (LOF) - on the CICIDS2017 dataset under two scenarios: detecting known attack types and generalizing to previously unseen threats. O…

Optimal Parameter Design for Power Electronic Converters Using a Probabilistic Learning-Based Stochastic Surrogate Model
Akash Mahajan, Shivam Chaturvedi, Srijita Das, Wencong Su, Van-Hai Bui
https://arxiv.org/abs/2506.20987

Optimal Parameter Design for Power Electronic Converters Using a Probabilistic Learning-Based Stochastic Surrogate Model
The selection of optimal design for power electronic converter parameters involves balancing efficiency and thermal constraints to ensure high performance without compromising safety. This paper introduces a probabilistic-learning-based stochastic surrogate modeling framework to address this challenge and significantly reduce the time required during the design phase. The approach begins with a neural network classifier that evaluates the feasibility of parameter configurations, effectively fil…

Heterogeneous Temporal Hypergraph Neural Network
Huan Liu, Pengfei Jiao, Mengzhou Gao, Chaochao Chen, Di Jin
https://arxiv.org/abs/2506.17312 https://

Heterogeneous Temporal Hypergraph Neural Network
Graph representation learning (GRL) has emerged as an effective technique for modeling graph-structured data. When modeling heterogeneity and dynamics in real-world complex networks, GRL methods designed for complex heterogeneous temporal graphs (HTGs) have been proposed and have achieved successful applications in various fields. However, most existing GRL methods mainly focus on preserving the low-order topology information while ignoring higher-order group interaction relationships, which ar…

IKEBANA: A Neural-Network approach for the K-shell ionization by electron impact
D. M. Mitnik, C. C. Montanari, S. Segui, S. P. Limandri, J. A. Guzm\'an, A. C. Carreras, J. C. Trincavelli
https://arxiv.org/abs/2506.20604

AE-PINNs: Attention-enhanced physics-informed neural networks for solving elliptic interface problems
Jiachun Zheng, Yunqing Huang, Nianyu Yi
https://arxiv.org/abs/2506.18332

AE-PINNs: Attention-enhanced physics-informed neural networks for solving elliptic interface problems
Inspired by the attention mechanism, we develop an attention-enhanced physics-informed neural networks (AE-PINNs) for solving elliptic interface equations. In AE-PINNs, we decompose the solution into two complementary components: a continuous component and a component with discontinuities across the interface. The continuous component is approximated by a fully connected neural network in the whole domain, while the discontinuous component is approximated by an interface-attention neural networ…

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

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

When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
Chen Zeno, Hila Manor, Greg Ongie, Nir Weinberger, Tomer Michaeli, Daniel Soudry
https://arxiv.org/abs/2506.19031

When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
While diffusion models generate high-quality images via probability flow, the theoretical understanding of this process remains incomplete. A key question is when probability flow converges to training samples or more general points on the data manifold. We analyze this by studying the probability flow of shallow ReLU neural network denoisers trained with minimal $\ell^2$ norm. For intuition, we introduce a simpler score flow and show that for orthogonal datasets, both flows follow similar traj…

Replaced article(s) found for quant-ph. https://arxiv.org/list/quant-ph/new
[2/2]:
- Probing Quantum Spin Systems with Kolmogorov-Arnold Neural Network Quantum States
Mahmud Ashraf Shamim, Eric A F Reinhardt, Talal Ahmed Chowdhury, Sergei Gleyzer, Paulo T Araujo

Analysis of Anonymous User Interaction Relationships and Prediction of Advertising Feedback Based on Graph Neural Network
Yanjun Dai, Haoyang Feng, Yuan Gao
https://arxiv.org/abs/2506.13787

Analysis of Anonymous User Interaction Relationships and Prediction of Advertising Feedback Based on Graph Neural Network
While online advertising is highly dependent on implicit interaction networks of anonymous users for engagement inference, and for the selection and optimization of delivery strategies, existing graph models seldom can capture the multi-scale temporal, semantic and higher-order dependency features of these interaction networks, thus it's hard to describe the complicated patterns of the anonymous behavior. In this paper, we propose Decoupled Temporal-Hierarchical Graph Neural Network (DTH-GNN), …

Deep learning inference with the #EventHorizonTelescope I. Calibration improvements and a comprehensive synthetic data library / II. The ZINGULARITY framework for Bayesian artificial neural networks / III. ZINGULARITY results from the 2017 observations and predictions for future array expansions: https://www.aanda.org/articles/aa/full_html/2025/06/aa53784-25/aa53784-25.html / https://www.aanda.org/articles/aa/full_html/2025/06/aa53785-25/aa53785-25.html / https://www.aanda.org/articles/aa/full_html/2025/06/aa53786-25/aa53786-25.html -> Self-learning neural network cracks iconic black holes: https://www.astronomie.nl/nieuws/en/self-learning-neural-network-cracks-iconic-black-holes-4528

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

"Brain-only participants exhibited the strongest, most distributed networks; Search Engine users showed moderate engagement; and LLM users displayed the weakest connectivity."
"LLM users also struggled to accurately quote their own work."
"Over four months, LLM users consistently underperformed at neural, linguistic, and behavioral levels."

Solving the QCD effective kinetic theory with neural networks
Sergio Barrera Cabodevila, Aleksi Kurkela, Florian Lindenbauer
https://arxiv.org/abs/2506.19632

Solving the QCD effective kinetic theory with neural networks
Event-by-event QCD kinetic theory simulations are hindered by the large numerical cost of evaluating the high-dimensional collision integral in the Boltzmann equation. In this work, we show that a neural network can be used to obtain an accurate estimate of the collision integral in a fraction of the time required for the ordinary Monte Carlo evaluation of the integral. We demonstrate that for isotropic and anisotropic distribution functions, the network accurately predicts the time evolution o…

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

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

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…

Embedded FPGA Acceleration of Brain-Like Neural Networks: Online Learning to Scalable Inference
Muhammad Ihsan Al Hafiz, Naresh Ravichandran, Anders Lansner, Pawel Herman, Artur Podobas
https://arxiv.org/abs/2506.18530

Embedded FPGA Acceleration of Brain-Like Neural Networks: Online Learning to Scalable Inference
Edge AI applications increasingly require models that can learn and adapt on-device with minimal energy budget. Traditional deep learning models, while powerful, are often overparameterized, energy-hungry, and dependent on cloud connectivity. Brain-Like Neural Networks (BLNNs), such as the Bayesian Confidence Propagation Neural Network (BCPNN), propose a neuromorphic alternative by mimicking cortical architecture and biologically-constrained learning. They offer sparse architectures with local …

A Unified Platform to Evaluate STDP Learning Rule and Synapse Model using Pattern Recognition in a Spiking Neural Network
Jaskirat Singh Maskeen, Sandip Lashkare
https://arxiv.org/abs/2506.19377

A Unified Platform to Evaluate STDP Learning Rule and Synapse Model using Pattern Recognition in a Spiking Neural Network
We develop a unified platform to evaluate Ideal, Linear, and Non-linear $\text{Pr}_{0.7}\text{Ca}_{0.3}\text{MnO}_{3}$ memristor-based synapse models, each getting progressively closer to hardware realism, alongside four STDP learning rules in a two-layer SNN with LIF neurons and adaptive thresholds for five-class MNIST classification. On MNIST with small train set and large test set, our two-layer SNN with ideal, 25-state, and 12-state nonlinear memristor synapses achieves 92.73 %, 91.07 %, an…

Fast State-Augmented Learning for Wireless Resource Allocation with Dual Variable Regression
Yigit Berkay Uslu, Navid NaderiAlizadeh, Mark Eisen, Alejandro Ribeiro
https://arxiv.org/abs/2506.18748

Fast State-Augmented Learning for Wireless Resource Allocation with Dual Variable Regression
We consider resource allocation problems in multi-user wireless networks, where the goal is to optimize a network-wide utility function subject to constraints on the ergodic average performance of users. We demonstrate how a state-augmented graph neural network (GNN) parametrization for the resource allocation policy circumvents the drawbacks of the ubiquitous dual subgradient methods by representing the network configurations (or states) as graphs and viewing dual variables as dynamic inputs t…

Integrating Vehicle Acoustic Data for Enhanced Urban Traffic Management: A Study on Speed Classification in Suzhou
Pengfei Fan, Yuli Zhang, Xinheng Wang, Ruiyuan Jiang, Hankang Gu, Dongyao Jia, Shangbo Wang
https://arxiv.org/abs/2506.21269

Integrating Vehicle Acoustic Data for Enhanced Urban Traffic Management: A Study on Speed Classification in Suzhou
This study presents and publicly releases the Suzhou Urban Road Acoustic Dataset (SZUR-Acoustic Dataset), which is accompanied by comprehensive data-acquisition protocols and annotation guidelines to ensure transparency and reproducibility of the experimental workflow. To model the coupling between vehicular noise and driving speed, we propose a bimodal-feature-fusion deep convolutional neural network (BMCNN). During preprocessing, an adaptive denoising and normalization strategy is applied to …

Diffusion-based Task-oriented Semantic Communications with Model Inversion Attack
Xuesong Wang, Mo Li, Xingyan Shi, Zhaoqian Liu, Shenghao Yang
https://arxiv.org/abs/2506.19886

Diffusion-based Task-oriented Semantic Communications with Model Inversion Attack
Semantic communication has emerged as a promising neural network-based system design for 6G networks. Task-oriented semantic communication is a novel paradigm whose core goal is to efficiently complete specific tasks by transmitting semantic information, optimizing communication efficiency and task performance. The key challenge lies in preserving privacy while maintaining task accuracy, as this scenario is susceptible to model inversion attacks. In such attacks, adversaries can restore or even…

Bridging Equilibrium and Kinetics Prediction with a Data-Weighted Neural Network Model of Methane Steam Reforming
Zofia Pizo\'n, Shinji Kimijima, Grzegorz Brus
https://arxiv.org/abs/2506.17224

Bridging Equilibrium and Kinetics Prediction with a Data-Weighted Neural Network Model of Methane Steam Reforming
Hydrogen's role is growing as an energy carrier, increasing the need for efficient production, with methane steam reforming being the most widely used technique. This process is crucial for applications like fuel cells, where hydrogen is converted into electricity, pushing for reactor miniaturization and optimized process control through numerical simulations. Existing models typically address either kinetic or equilibrium regimes, limiting their applicability. Here we show a surrogate model ca…

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:

Active Learning for Manifold Gaussian Process Regression
Yuanxing Cheng, Lulu Kang, Yiwei Wang, Chun Liu
https://arxiv.org/abs/2506.20928 https://

Active Learning for Manifold Gaussian Process Regression
This paper introduces an active learning framework for manifold Gaussian Process (GP) regression, combining manifold learning with strategic data selection to improve accuracy in high-dimensional spaces. Our method jointly optimizes a neural network for dimensionality reduction and a Gaussian process regressor in the latent space, supervised by an active learning criterion that minimizes global prediction error. Experiments on synthetic data demonstrate superior performance over randomly sequen…

Vortex-Induced Drag Forecast for Cylinder in Non-uniform Inflow
Jiashun Guan, Haoyang Hu, Tianfang Hao, Huimin Wang, Yunxiao Ren, Dixia Fan
https://arxiv.org/abs/2506.21075

Vortex-Induced Drag Forecast for Cylinder in Non-uniform Inflow
In this letter, a physics-based data-driven strategy is developed to predict vortex-induced drag on a circular cylinder under non-uniform inflow conditions - a prevalent issue for engineering applications at moderate Reynolds numbers. Traditional pressure-signal-based models exhibit limitations due to complex vortex dynamics coupled with non-uniform inflow. To address this issue, a modified fully connected neural network (FCNN) architecture is established that integrates upstream velocity measu…

ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
Ahmad Mustafa, Reza Rastegar, Ghassan AlRegib
https://arxiv.org/abs/2506.19687 …

ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
Prostate gland segmentation from T2-weighted MRI is a critical yet challenging task in clinical prostate cancer assessment. While deep learning-based methods have significantly advanced automated segmentation, most conventional approaches-particularly 2D convolutional neural networks (CNNs)-fail to leverage inter-slice anatomical continuity, limiting their accuracy and robustness. Fully 3D models offer improved spatial coherence but require large amounts of annotated data, which is often imprac…

Numerical simulation of transient heat conduction with moving heat source using Physics Informed Neural Networks
Anirudh Kalyan, Sundararajan Natarajan
https://arxiv.org/abs/2506.17726

Numerical simulation of transient heat conduction with moving heat source using Physics Informed Neural Networks
In this paper, the physics informed neural networks (PINNs) is employed for the numerical simulation of heat transfer involving a moving source. To reduce the computational effort, a new training method is proposed that uses a continuous time-stepping through transfer learning. Within this, the time interval is divided into smaller intervals and a single network is initialized. On this single network each time interval is trained with the initial condition for (n+1)th as the solution obtained a…

Neural networks for the prediction of peel force for skin adhesive interface using FEM simulation
Ashish Masarkar, Rakesh Gupta, Naga Neehar Dingari, Beena Rai
https://arxiv.org/abs/2506.19855

Neural networks for the prediction of peel force for skin adhesive interface using FEM simulation
Studying the peeling behaviour of adhesives on skin is vital for advancing biomedical applications such as medical adhesives and transdermal patches. Traditional methods like experimental testing and finite element method (FEM), though considered gold standards, are resource-intensive, computationally expensive and time-consuming, particularly when analysing a wide material parameter space. In this study, we present a neural network-based approach to predict the minimum peel force (F_min) requi…

Decision-Focused Learning for Neural Network-Constrained Optimization: Application to HVAC Management System
Pietro Favaro, Jean-Fran\c{c}ois Toubeau, Fran\c{c}ois Vall\'ee, Yury Dvorkin
https://arxiv.org/abs/2506.19717

Decision-Focused Learning for Neural Network-Constrained Optimization: Application to HVAC Management System
Heating, Ventilation, and Air Conditioning (HVAC) is a major electricity end-use with a substantial potential for grid services such as demand response. Harnessing this flexibility requires accurate modeling of the thermal dynamics of buildings, which is challenging due to their nonlinear and repetitive behavior (e.g., daily pattern), which reduce the value of historical data. To address this issue, this paper presents an HVAC management system formulated as a Mixed Integer Quadratic Program (M…

Demographics-Informed Neural Network for Multi-Modal Spatiotemporal forecasting of Urban Growth and Travel Patterns Using Satellite Imagery
Eugene Kofi Okrah Denteh, Andrews Danyo, Joshua Kofi Asamoah, Blessing Agyei Kyem, Armstrong Aboah
https://arxiv.org/abs/2506.12456

Demographics-Informed Neural Network for Multi-Modal Spatiotemporal forecasting of Urban Growth and Travel Patterns Using Satellite Imagery
This study presents a novel demographics informed deep learning framework designed to forecast urban spatial transformations by jointly modeling geographic satellite imagery, socio-demographics, and travel behavior dynamics. The proposed model employs an encoder-decoder architecture with temporal gated residual connections, integrating satellite imagery and demographic data to accurately forecast future spatial transformations. The study also introduces a demographics prediction component which…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[6/9]:
- Knowledge Distillation Framework for Accelerating High-Accuracy Neural Network-Based Molecular Dy...
Naoki Matsumura, Yuta Yoshimoto, Yuto Iwasaki, Meguru Yamazaki, Yasufumi Sakai

Simulation of a closed-loop dc-dc converter using a physics-informed neural network-based model
Marc-Antoine Coulombe, Maxime Berger, Antoine Lesage-Landry
https://arxiv.org/abs/2506.19178

Simulation of a closed-loop dc-dc converter using a physics-informed neural network-based model
The growing reliance on power electronics introduces new challenges requiring detailed time-domain analyses with fast and accurate circuit simulation tools. Currently, commercial time-domain simulation software are mainly relying on physics-based methods to simulate power electronics. Recent work showed that data-driven and physics-informed learning methods can increase simulation speed with limited compromise on accuracy, but many challenges remain before deployment in commercial tools can be …

Learning to Maximize Quantum Neural Network Expressivity via Effective Rank
Juan Yao
https://arxiv.org/abs/2506.15375 https://arxiv.o…

Learning to Maximize Quantum Neural Network Expressivity via Effective Rank
Quantum neural networks (QNNs) are widely employed as ansätze for solving variational problems, where their expressivity directly impacts performance. Yet, accurately characterizing QNN expressivity remains an open challenge, impeding the optimal design of quantum circuits. In this work, we introduce the effective rank, denoted as $κ$, as a novel quantitative measure of expressivity. Specifically, $κ$ captures the number of effectively independent parameters among all the variational paramet…

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 …

The Condition Number as a Scale-Invariant Proxy for Information Encoding in Neural Units
Oswaldo Ludwig
https://arxiv.org/abs/2506.16289 https://

The Condition Number as a Scale-Invariant Proxy for Information Encoding in Neural Units
This paper explores the relationship between the condition number of a neural network's weight tensor and the extent of information encoded by the associated processing unit, viewed through the lens of information theory. We argue that a high condition number, though not sufficient for effective knowledge encoding, may indicate that the unit has learned to selectively amplify and compress information. We formalize this intuition, particularly for linear units with Gaussian inputs, linking the c…

Multimodal Visual Image Based User Association and Beamforming Using Graph Neural Networks
Yinghan Li, Yiming Liu, Wei Yu
https://arxiv.org/abs/2506.18218 …

Multimodal Visual Image Based User Association and Beamforming Using Graph Neural Networks
This paper proposes an approach that leverages multimodal data by integrating visual images with radio frequency (RF) pilots to optimize user association and beamforming in a downlink wireless cellular network under a max-min fairness criterion. Traditional methods typically optimize wireless system parameters based on channel state information (CSI). However, obtaining accurate CSI requires extensive pilot transmissions, which lead to increased overhead and latency. Moreover, the optimization …

ANIRA: An Architecture for Neural Network Inference in Real-Time Audio Applications
Valentin Ackva, Fares Schulz
https://arxiv.org/abs/2506.12665 https://

ANIRA: An Architecture for Neural Network Inference in Real-Time Audio Applications
Numerous tools for neural network inference are currently available, yet many do not meet the requirements of real-time audio applications. In response, we introduce anira, an efficient cross-platform library. To ensure compatibility with a broad range of neural network architectures and frameworks, anira supports ONNX Runtime, LibTorch, and TensorFlow Lite as backends. Each inference engine exhibits real-time violations, which anira mitigates by decoupling the inference from the audio callback…

Integrated photonic deep neural network with end-to-end on-chip backpropagation training
Farshid Ashtiani, Mohamad Hossein Idjadi, Kwangwoong Kim
https://arxiv.org/abs/2506.14575 …

Integrated photonic deep neural network with end-to-end on-chip backpropagation training
Integrated photonic neural networks (PNNs) have demonstrated significant potential to complement the digital electronic counterparts [1-3]. Nevertheless, robust and repeatable performance of scalable integrated PNNs is directly tied to the quality of their training. Error backpropagation (BP), which relies on nonlinear activation gradient computation, is the mainstream algorithm to train digital neural networks due to its scalability, versatility, and implementation efficiency [4]. Consequently…

Inferring viscoplastic models from velocity fields: a physics-informed neural network approach
Martin Lardy, Sham Tlili, Simon Gsell
https://arxiv.org/abs/2506.17681

Inferring viscoplastic models from velocity fields: a physics-informed neural network approach
Fluid-like materials are ubiquitous, spanning from living biological tissues to geological formations, and across scales ranging from micrometers to kilometers. Inferring their rheological properties remains a major challenge, particularly when traditional rheometry fails to capture their complex, three-dimensional, and often heterogeneous behavior. This difficulty is exacerbated by system size, boundary conditions, and other material-specific physical, chemical, or thermal constraints. In this…

DPG loss functions for learning parameter-to-solution maps by neural networks
Pablo Cort\'es Castillo, Wolfgang Dahmen, Jay Gopalakrishnan
https://arxiv.org/abs/2506.18773

DPG loss functions for learning parameter-to-solution maps by neural networks
We develop, analyze, and experimentally explore residual-based loss functions for machine learning of parameter-to-solution maps in the context of parameter-dependent families of partial differential equations (PDEs). Our primary concern is on rigorous accuracy certification to enhance prediction capability of resulting deep neural network reduced models. This is achieved by the use of variationally correct loss functions. Through one specific example of an elliptic PDE, details for establishin…

Towards Unified Neural Decoding with Brain Functional Network Modeling
Di Wu, Linghao Bu, Yifei Jia, Lu Cao, Siyuan Li, Siyu Chen, Yueqian Zhou, Sheng Fan, Wenjie Ren, Dengchang Wu, Kang Wang, Yue Zhang, Yuehui Ma, Jie Yang, Mohamad Sawan
https://arxiv.org/abs/2506.12055

Towards Unified Neural Decoding with Brain Functional Network Modeling
Recent achievements in implantable brain-computer interfaces (iBCIs) have demonstrated the potential to decode cognitive and motor behaviors with intracranial brain recordings; however, individual physiological and electrode implantation heterogeneities have constrained current approaches to neural decoding within single individuals, rendering interindividual neural decoding elusive. Here, we present Multi-individual Brain Region-Aggregated Network (MIBRAIN), a neural decoding framework that co…

J3DAI: A tiny DNN-Based Edge AI Accelerator for 3D-Stacked CMOS Image Sensor
Benoit Tain, Raphael Millet, Romain Lemaire, Michal Szczepanski, Laurent Alacoque, Emmanuel Pluchart, Sylvain Choisnet, Rohit Prasad, Jerome Chossat, Pascal Pierunek, Pascal Vivet, Sebastien Thuries
https://arxiv.org/abs/2506.15316

J3DAI: A tiny DNN-Based Edge AI Accelerator for 3D-Stacked CMOS Image Sensor
This paper presents J3DAI, a tiny deep neural network-based hardware accelerator for a 3-layer 3D-stacked CMOS image sensor featuring an artificial intelligence (AI) chip integrating a Deep Neural Network (DNN)-based accelerator. The DNN accelerator is designed to efficiently perform neural network tasks such as image classification and segmentation. This paper focuses on the digital system of J3DAI, highlighting its Performance-Power-Area (PPA) characteristics and showcasing advanced edge AI c…

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…

SecONNds: Secure Outsourced Neural Network Inference on ImageNet
Shashank Balla
https://arxiv.org/abs/2506.11586 https://arxiv.org/pd…

SecONNds: Secure Outsourced Neural Network Inference on ImageNet
The widespread adoption of outsourced neural network inference presents significant privacy challenges, as sensitive user data is processed on untrusted remote servers. Secure inference offers a privacy-preserving solution, but existing frameworks suffer from high computational overhead and communication costs, rendering them impractical for real-world deployment. We introduce SecONNds, a non-intrusive secure inference framework optimized for large ImageNet-scale Convolutional Neural Networks. …

Frequency Control in Microgrids: An Adaptive Fuzzy-Neural-Network Virtual Synchronous Generator
Waleed Breesam, Rezvan Alamian, Nima Tashakor, Brahim Elkhalil Youcefa, Stefan M. Goetz
https://arxiv.org/abs/2506.18611

Frequency Control in Microgrids: An Adaptive Fuzzy-Neural-Network Virtual Synchronous Generator
The reliance on distributed renewable energy has increased recently. As a result, power electronic-based distributed generators replaced synchronous generators which led to a change in the dynamic characteristics of the microgrid. Most critically, they reduced system inertia and damping. Virtual synchronous generators emulated in power electronics, which mimic the dynamic behaviour of synchronous generators, are meant to fix this problem. However, fixed virtual synchronous generator parameters …

NeRF-based CBCT Reconstruction needs Normalization and Initialization
Zhuowei Xu, Han Li, Dai Sun, Zhicheng Li, Yujia Li, Qingpeng Kong, Zhiwei Cheng, Nassir Navab, S. Kevin Zhou
https://arxiv.org/abs/2506.19742

NeRF-based CBCT Reconstruction needs Normalization and Initialization
Cone Beam Computed Tomography (CBCT) is widely used in medical imaging. However, the limited number and intensity of X-ray projections make reconstruction an ill-posed problem with severe artifacts. NeRF-based methods have achieved great success in this task. However, they suffer from a local-global training mismatch between their two key components: the hash encoder and the neural network. Specifically, in each training step, only a subset of the hash encoder's parameters is used (local sparse…

This https://arxiv.org/abs/2505.18565 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning Fluid-Structure Interaction Dynamics with Physics-Informed Neural Networks and Immersed Boundary Methods
We introduce neural network architectures that combine physics-informed neural networks (PINNs) with the immersed boundary method (IBM) to solve fluid-structure interaction (FSI) problems. Our approach features two distinct architectures: a Single-FSI network with a unified parameter space, and an innovative Eulerian-Lagrangian network that maintains separate parameter spaces for fluid and structure domains. We study each architecture using standard Tanh and adaptive B-spline activation functio…

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…

Sequence-to-Sequence Models with Attention Mechanistically Map to the Architecture of Human Memory Search
Nikolaus Salvatore, Qiong Zhang
https://arxiv.org/abs/2506.17424

Sequence-to-Sequence Models with Attention Mechanistically Map to the Architecture of Human Memory Search
Past work has long recognized the important role of context in guiding how humans search their memory. While context-based memory models can explain many memory phenomena, it remains unclear why humans develop such architectures over possible alternatives in the first place. In this work, we demonstrate that foundational architectures in neural machine translation -- specifically, recurrent neural network (RNN)-based sequence-to-sequence models with attention -- exhibit mechanisms that directly…

A Synthetic Pseudo-Autoencoder Invites Examination of Tacit Assumptions in Neural Network Design
Assaf Marron
https://arxiv.org/abs/2506.12076 https://

A Synthetic Pseudo-Autoencoder Invites Examination of Tacit Assumptions in Neural Network Design
We present a handcrafted neural network that, without training, solves the seemingly difficult problem of encoding an arbitrary set of integers into a single numerical variable, and then recovering the original elements. While using only standard neural network operations -- weighted sums with biases and identity activation -- we make design choices that challenge common notions in this area around representation, continuity of domains, computation, learnability and more. For example, our const…

Learning Magnitude Distribution of Sound Fields via Conditioned Autoencoder
Shoichi Koyama, Kenji Ishizuka
https://arxiv.org/abs/2506.16729 https://…

Learning Magnitude Distribution of Sound Fields via Conditioned Autoencoder
A learning-based method for estimating the magnitude distribution of sound fields from spatially sparse measurements is proposed. Estimating the magnitude distribution of acoustic transfer function (ATF) is useful when phase measurements are unreliable or inaccessible and has a wide range of applications related to spatial audio. We propose a neural-network-based method for the ATF magnitude estimation. The key feature of our network architecture is the input and output layers conditioned on so…

Temperature calibration of surface emissivities with an improved thermal image enhancement network
Ning Chu, Siya Zheng, Shanqing Zhang, Li Li, Caifang Cai, Ali Mohammad-Djafari, Feng Zhao, Yuanbo Song
https://arxiv.org/abs/2506.16803

Temperature calibration of surface emissivities with an improved thermal image enhancement network
Infrared thermography faces persistent challenges in temperature accuracy due to material emissivity variations, where existing methods often neglect the joint optimization of radiometric calibration and image degradation. This study introduces a physically guided neural framework that unifies temperature correction and image enhancement through a symmetric skip-CNN architecture and an emissivity-aware attention module. The pre-processing stage segments the ROIs of the image and and initially c…

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

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

Explicit Residual-Based Scalable Image Coding for Humans and Machines
Yui Tatsumi, Ziyue Zeng, Hiroshi Watanabe
https://arxiv.org/abs/2506.19297 https://…

Explicit Residual-Based Scalable Image Coding for Humans and Machines
Scalable image compression is a technique that progressively reconstructs multiple versions of an image for different requirements. In recent years, images have increasingly been consumed not only by humans but also by image recognition models. This shift has drawn growing attention to scalable image compression methods that serve both machine and human vision (ICMH). Many existing models employ neural network-based codecs, known as learned image compression, and have made significant strides i…

Weak TransNet: A Petrov-Galerkin based neural network method for solving elliptic PDEs
Zhihang Xu, Min Wang, Zhu Wang
https://arxiv.org/abs/2506.14812 http…

Weak TransNet: A Petrov-Galerkin based neural network method for solving elliptic PDEs
While deep learning has achieved remarkable success in solving partial differential equations (PDEs), it still faces significant challenges, particularly when the PDE solutions have low regularity or singularities. To address these issues, we propose the Weak TransNet (WTN) method, based on a Petrov-Galerkin formulation, for solving elliptic PDEs in this work, though its framework may extend to other classes of equations. Specifically, the neural feature space defined by TransNet (Zhang et al.,…

Learning to assess subjective impressions from speech
Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Noboru Harada
https://arxiv.org/abs/2506.19335

Learning to assess subjective impressions from speech
We tackle a new task of training neural network models that can assess subjective impressions conveyed through speech and assign scores accordingly, inspired by the work on automatic speech quality assessment (SQA). Speech impressions are often described using phrases like `cute voice.' We define such phrases as subjective voice descriptors (SVDs). Focusing on the difference in usage scenarios between the proposed task and automatic SQA, we design a framework capable of accommodating SVDs perso…

Online-Optimized Gated Radial Basis Function Neural Network-Based Adaptive Control
Mingcong Li
https://arxiv.org/abs/2506.13168 https://

Online-Optimized Gated Radial Basis Function Neural Network-Based Adaptive Control
Real-time adaptive control of nonlinear systems with unknown dynamics and time-varying disturbances demands precise modeling and robust parameter adaptation. While existing neural network-based strategies struggle with computational inefficiency or inadequate temporal dependencies, this study proposes a hybrid control framework integrating a Temporal-Gated Radial Basis Function (TGRBF) network with a nonlinear robust controller. The TGRBF synergizes radial basis function neural networks (RBFNNs…

NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning
Ashish Gautam, Prasanna Date, Shruti Kulkarni, Robert Patton, Thomas Potok
https://arxiv.org/abs/2506.14138

NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning
Spiking Neural Networks (SNNs) are computational models inspired by the structure and dynamics of biological neuronal networks. Their event-driven nature enables them to achieve high energy efficiency, particularly when deployed on neuromorphic hardware platforms. Unlike conventional Artificial Neural Networks (ANNs), which primarily rely on layered architectures, SNNs naturally support a wide range of connectivity patterns, from traditional layered structures to small-world graphs characterize…

A Hybrid Neural Network -- Polynomial Series Scheme for Learning Invariant Manifolds of Discrete Dynamical Systems
Dimitrios G. Patsatzis, Nikolaos Kazantzis, Ioannis G. Kevrekidis, Constantinos Siettos
https://arxiv.org/abs/2506.13950

A Hybrid Neural Network -- Polynomial Series Scheme for Learning Invariant Manifolds of Discrete Dynamical Systems
We propose a hybrid machine learning scheme to learn -- in physics-informed and numerical analysis-informed fashion -- invariant manifolds (IM) of discrete maps for constructing reduced-order models (ROMs) for dynamical systems. The proposed scheme combines polynomial series with shallow neural networks, exploiting the complementary strengths of both approaches. Polynomials enable an efficient and accurate modeling of ROMs with guaranteed local exponential convergence rate around the fixed poin…

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…