Tootfinder

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

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

Neural Network-based Information-Theoretic Transceivers for High-Order Modulation Schemes
Ngoc Long Pham, Tri Nhu Do
https://arxiv.org/abs/2506.00368 https…

Neural Network-based Information-Theoretic Transceivers for High-Order Modulation Schemes
Neural network (NN)-based end-to-end (E2E) communication systems, in which each system component may consist of a portion of a neural network, have been investigated as potential tools for developing artificial intelligence (Al)-native E2E systems. In this paper, we propose an NN-based bitwise receiver that improves computational efficiency while maintaining performance comparable to baseline demappers. Building on this foundation, we introduce a novel symbol-wise autoencoder (AE)-based E2E sys…

Unsupervised Sparse Coding-based Spiking Neural Network for Real-time Spike Sorting
Alexis Melot, Sean U. N. Wood, Yannick Coffinier, Pierre Yger, Fabien Alibart
https://arxiv.org/abs/2506.24041

Unsupervised Sparse Coding-based Spiking Neural Network for Real-time Spike Sorting
Spike sorting is a crucial step in decoding multichannel extracellular neural signals, enabling the identification of individual neuronal activity. A key challenge in brain-machine interfaces (BMIs) is achieving real-time, low-power spike sorting at the edge while keeping high neural decoding performance. This study introduces the Neuromorphic Sparse Sorter (NSS), a compact two-layer spiking neural network optimized for efficient spike sorting. NSS leverages the Locally Competitive Algorithm (L…

Large-scale Neural Network Quantum States for ab initio Quantum Chemistry Simulations on Fugaku
Hongtao Xu, Zibo Wu, Mingzhen Li, Weile Jia
https://arxiv.org/abs/2506.23809

Large-scale Neural Network Quantum States for ab initio Quantum Chemistry Simulations on Fugaku
Solving quantum many-body problems is one of the fundamental challenges in quantum chemistry. While neural network quantum states (NQS) have emerged as a promising computational tool, its training process incurs exponentially growing computational demands, becoming prohibitively expensive for large-scale molecular systems and creating fundamental scalability barriers for real-world applications. To address above challenges, we present \ours, a high-performance NQS training framework for \textit…

A2 Copula-Driven Spatial Bayesian Neural Network For Modeling Non-Gaussian Dependence: A Simulation Study
Agnideep Aich, Sameera Hewage, Md Monzur Murshed, Ashit Baran Aich, Amanda Mayeaux, Asim K. Dey, Kumer P. Das, Bruce Wade
https://arxiv.org/abs/2505.24006

A2 Copula-Driven Spatial Bayesian Neural Network For Modeling Non-Gaussian Dependence: A Simulation Study
In this paper, we introduce the A2 Copula Spatial Bayesian Neural Network (A2-SBNN), a predictive spatial model designed to map coordinates to continuous fields while capturing both typical spatial patterns and extreme dependencies. By embedding the dual-tail novel Archimedean copula viz. A2 directly into the network's weight initialization, A2-SBNN naturally models complex spatial relationships, including rare co-movements in the data. The model is trained through a calibration-driven process …

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

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

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…

Feature Integration Spaces: Joint Training Reveals Dual Encoding in Neural Network Representations
Omar Claflin
https://arxiv.org/abs/2507.00269 https://…

Feature Integration Spaces: Joint Training Reveals Dual Encoding in Neural Network Representations
Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs consistently fail to eliminate polysemanticity and exhibit pathological behavioral errors. We propose that neural networks encode information in two complementary spaces compressed into the same substrate: feature identity and feature integration. To test this dual enc…

Seeding neural network quantum states with tensor network states
Ryui Kaneko, Shimpei Goto
https://arxiv.org/abs/2506.23550 https://a…

Seeding neural network quantum states with tensor network states
We find an efficient approach to approximately convert matrix product states (MPSs) into restricted Boltzmann machine wave functions consisting of a multinomial hidden unit through a canonical polyadic (CP) decomposition of the MPSs. This method allows us to generate well-behaved initial neural network quantum states for quantum many-body ground-state calculations in polynomial time of the number of variational parameters and systematically shorten the distance between the initial states and th…

Anthropic details "persona vectors", patterns of activity within an AI model's neural network that control its character traits, such as evil and sycophancy (Anthropic)
https://www.anthropic.com/research/persona-vectors

Persona vectors: Monitoring and controlling character traits in language models
A paper from Anthropic describing persona vectors and their applications to monitoring and controlling model behavior

Multi-Objective Neural Network Assisted Design Optimization of Soft Fin-Ray Grippers for Enhanced Grasping Performance
Ali Ghanizadeh, Ali Ahmadi, Arash Bahrami
https://arxiv.org/abs/2506.00494

Multi-Objective Neural Network Assisted Design Optimization of Soft Fin-Ray Grippers for Enhanced Grasping Performance
Soft Fin-Ray grippers can perform delicate and careful manipulation, which has caused notable attention in different fields. These grippers can handle objects of various forms and sizes safely. The internal structure of the Fin-Ray finger plays a significant role in its adaptability and grasping performance. However, modeling the non-linear grasp force and deformation behaviors for design purposes is challenging. Moreover, when the Fin-Ray finger becomes more rigid and capable of exerting highe…

Search for $t\bar tt\bar tW$ Production at $\sqrt{s} = 13$ TeV Using a Modified Graph Neural Network at the LHC
Syed Haider Ali, Ashfaq Ahmad, Muhammad Saiel, Nadeem Shaukat
https://arxiv.org/abs/2507.23723

Search for $t\bar tt\bar tW$ Production at $\sqrt{s} = 13$ TeV Using a Modified Graph Neural Network at the LHC
The simultaneous production of four top quarks in association with a ($W$) boson at $(\sqrt{s} = 13)$ TeV is an rare SM process with a next-to-leading-order (NLO) cross-section of $(6.6^{+2.4}_{-2.6} {ab})$\cite{saiel}. Identifying this process in the fully hadronic decay channel is particularly challenging due to overwhelming backgrounds from $t\bar{t}, t\bar{t}W, t\bar{t}Z$, and triple-top production processes. This study introduces a modified physics informed Neural Network, a hybrid graph n…

Neural Network-based Universal Formulas for Control
Pol Mestres, Jorge Cort\'es, Eduardo D. Sontag
https://arxiv.org/abs/2505.24744 https://

Neural Network-based Universal Formulas for Control
We study the problem of designing a controller that satisfies an arbitrary number of affine inequalities at every point in the state space. This is motivated by the use of guardrails in autonomous systems. Indeed, a variety of key control objectives, such as stability, safety, and input saturation, are guaranteed by closed-loop systems whose controllers satisfy such inequalities. Many works in the literature design such controllers as the solution to a state-dependent quadratic program (QP) who…

Decoding Cellular Temperature via Neural Network-Aided Fluorescent Thermometry
Tong Zhang, Tian-Tian Li, Jing-Ru Wang, Yu-Wen Zhang, Chao Sun, Zheng Huang, Jing-Juan Xu, Bin Kang
https://arxiv.org/abs/2506.00389

Decoding Cellular Temperature via Neural Network-Aided Fluorescent Thermometry
The temperature distribution within cells, especially the debates on mitochondrial temperature, has recently attracted widespread attention. Some studies have claimed that the temperature of mitochondria can reach up to 50-53 degrees Celsius. Yet others have questioned that this is due to measurement errors from fluorescent thermometry caused by other factors, like cell viscosity. Here we present a neural network-aided fluorescent thermometry and decouple the effect of cellular viscosity on tem…

Fine-Tuning MIDI-to-Audio Alignment using a Neural Network on Piano Roll and CQT Representations
Sebastian Murgul, Moritz Reiser, Michael Heizmann, Christoph Seibert
https://arxiv.org/abs/2506.22237

Fine-Tuning MIDI-to-Audio Alignment using a Neural Network on Piano Roll and CQT Representations
In this paper, we present a neural network approach for synchronizing audio recordings of human piano performances with their corresponding loosely aligned MIDI files. The task is addressed using a Convolutional Recurrent Neural Network (CRNN) architecture, which effectively captures spectral and temporal features by processing an unaligned piano roll and a spectrogram as inputs to estimate the aligned piano roll. To train the network, we create a dataset of piano pieces with augmented MIDI fil…

DiffCkt: A Diffusion Model-Based Hybrid Neural Network Framework for Automatic Transistor-Level Generation of Analog Circuits
Chengjie Liu, Jiajia Li, Yabing Feng, Wenhao Huang, Weiyu Chen, Yuan Du, Jun Yang, Li Du
https://arxiv.org/abs/2507.00444

DiffCkt: A Diffusion Model-Based Hybrid Neural Network Framework for Automatic Transistor-Level Generation of Analog Circuits
Analog circuit design consists of the pre-layout and layout phases. Among them, the pre-layout phase directly decides the final circuit performance, but heavily depends on experienced engineers to do manual design according to specific application scenarios. To overcome these challenges and automate the analog circuit pre-layout design phase, we introduce DiffCkt: a diffusion model-based hybrid neural network framework for the automatic transistor-level generation of analog circuits, which can …

Graph neural network model for the era of large atomistic models
Duo Zhang, Anyang Peng, Chun Cai, Wentao Li, Yuanchang Zhou, Jinzhe Zeng, Mingyu Guo, Chengqian Zhang, Bowen Li, Hong Jiang, Tong Zhu, Weile Jia, Linfeng Zhang, Han Wang
https://arxiv.org/abs/2506.01686

Graph neural network model for the era of large atomistic models
Foundation models, or large atomistic models (LAMs), aim to universally represent the ground-state potential energy surface (PES) of atomistic systems as defined by density functional theory (DFT). The scaling law is pivotal in the development of large models, suggesting that their generalizability in downstream tasks consistently improves with increased model size, expanded training datasets, and larger computational budgets. In this study, we present DPA3, a multi-layer graph neural network f…

Finally am setting up LLMs on my Proxmox server. And feeling very smart I overbuilt the machine a few years ago. Plenty of RAM and fast disk to store giant blobs of neural network weights.

Controller Design for Bilinear Neural Feedback Loops
Dhruv Shah, Jorge Cort\'es
https://arxiv.org/abs/2505.24106 https://arxiv.or…

Controller Design for Bilinear Neural Feedback Loops
This paper considers a class of bilinear systems with a neural network in the loop. These arise naturally when employing machine learning techniques to approximate general, non-affine in the input, control systems. We propose a controller design framework that combines linear fractional representations and tools from linear parameter varying control to guarantee local exponential stability of a desired equilibrium. The controller is obtained from the solution of linear matrix inequalities, whic…

This https://arxiv.org/abs/2409.15683 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Quantum DeepONet: Neural operators accelerated by quantum computing
In the realm of computational science and engineering, constructing models that reflect real-world phenomena requires solving partial differential equations (PDEs) with different conditions. Recent advancements in neural operators, such as deep operator network (DeepONet), which learn mappings between infinite-dimensional function spaces, promise efficient computation of PDE solutions for a new condition in a single forward pass. However, classical DeepONet entails quadratic complexity concerni…

This https://arxiv.org/abs/2505.23655 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Keyed Chaotic Tensor Transformations for Secure And Attributable Neural Inference
This work introduces a novel framework for secure and privacy-preserving neural network inference based on keyed chaotic dynamical transformations. The proposed method applies a deterministic, cryptographically seeded chaotic system to tensors, producing non-invertible, user-specific transformations that enable authenticated inference, tensor-level watermarking, and data attribution. This framework offers a scalable and lightweight alternative to conventional cryptographic techniques, and estab…

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

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

Physics-Informed Neural Networks for the Relativistic Burgers Equation in the Exterior of a Schwarzschild Black Hole
Shuyang Xiang
https://arxiv.org/abs/2506.00951

Physics-Informed Neural Networks for the Relativistic Burgers Equation in the Exterior of a Schwarzschild Black Hole
We introduce a Physics-Informed Neural Networks(PINN) to solve a relativistic Burgers equation in the exterior domain of a Schwarzschild black hole. Our main contribution is a PINN architecture that is able to simulate shock wave formations in such curved spacetime, by training a shock- aware network block and introducing a Godunov-inspired residuals in the loss function. We validate our method with numerical experiments with different kinds of initial conditions. We show its ability to reprodu…

Getting More from Less: Transfer Learning Improves Sleep Stage Decoding Accuracy in Peripheral Wearable Devices
William G Coon, Diego Luna, Akshita Panagrahi, Matthew Reid, Mattson Ogg
https://arxiv.org/abs/2506.00730

Getting More from Less: Transfer Learning Improves Sleep Stage Decoding Accuracy in Peripheral Wearable Devices
Transfer learning, a technique commonly used in generative artificial intelligence, allows neural network models to bring prior knowledge to bear when learning a new task. This study demonstrates that transfer learning significantly enhances the accuracy of sleep-stage decoding from peripheral wearable devices by leveraging neural network models pretrained on electroencephalographic (EEG) signals. Consumer wearable technologies typically rely on peripheral physiological signals such as pulse pl…

Estimating Head Motion in Structural MRI Using a Deep Neural Network Trained on Synthetic Artifacts
Charles Bricout, Samira Ebrahimi Kahou, Sylvain Bouix
https://arxiv.org/abs/2505.23916

Estimating Head Motion in Structural MRI Using a Deep Neural Network Trained on Synthetic Artifacts
Motion-related artifacts are inevitable in Magnetic Resonance Imaging (MRI) and can bias automated neuroanatomical metrics such as cortical thickness. Manual review cannot objectively quantify motion in anatomical scans, and existing automated approaches often require specialized hardware or rely on unbalanced noisy training data. Here, we train a 3D convolutional neural network to estimate motion severity using only synthetically corrupted volumes. We validate our method with one held-out site…

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

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

Neural Drift Estimation for Ergodic Diffusions: Non-parametric Analysis and Numerical Exploration
Simone Di Gregorio, Francesco Iafrate
https://arxiv.org/abs/2505.24383

Neural Drift Estimation for Ergodic Diffusions: Non-parametric Analysis and Numerical Exploration
We take into consideration generalization bounds for the problem of the estimation of the drift component for ergodic stochastic differential equations, when the estimator is a ReLU neural network and the estimation is non-parametric with respect to the statistical model. We show a practical way to enforce the theoretical estimation procedure, enabling inference on noisy and rough functional data. Results are shown for a simulated Itô-Taylor approximation of the sample paths.

Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems
Pedro R. Pires, Tiago A. Almeida
https://arxiv.org/abs/2506.22648

Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems
Over the past decade, recommender systems have experienced a surge in popularity. Despite notable progress, they grapple with challenging issues, such as high data dimensionality and sparseness. Representing users and items as low-dimensional embeddings learned via neural networks has become a leading solution. However, while recent studies show promising results, many approaches rely on complex architectures or require content data, which may not always be available. This paper presents Intera…

RaGNNarok: A Light-Weight Graph Neural Network for Enhancing Radar Point Clouds on Unmanned Ground Vehicles
David Hunt, Shaocheng Luo, Spencer Hallyburton, Shafii Nillongo, Yi Li, Tingjun Chen, Miroslav Pajic
https://arxiv.org/abs/2507.00937

RaGNNarok: A Light-Weight Graph Neural Network for Enhancing Radar Point Clouds on Unmanned Ground Vehicles
Low-cost indoor mobile robots have gained popularity with the increasing adoption of automation in homes and commercial spaces. However, existing lidar and camera-based solutions have limitations such as poor performance in visually obscured environments, high computational overhead for data processing, and high costs for lidars. In contrast, mmWave radar sensors offer a cost-effective and lightweight alternative, providing accurate ranging regardless of visibility. However, existing radar-base…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[8/9]:
- Benchmarking Spiking Neural Network Learning Methods with Varying Locality
Jiaqi Lin, Sen Lu, Malyaban Bal, Abhronil Sengupta

Classifying Hotspots Mutations for Biosimulation with Quantum Neural Networks and Variational Quantum Eigensolver
Don Roosan, Rubayat Khan, Saif Nirzhor, Tiffany Khou, Fahmida Hai
https://arxiv.org/abs/2507.00072

Classifying Hotspots Mutations for Biosimulation with Quantum Neural Networks and Variational Quantum Eigensolver
The rapid expansion of biomolecular datasets presents significant challenges for computational biology. Quantum computing emerges as a promising solution to address these complexities. This study introduces a novel quantum framework for analyzing TART-T and TART-C gene data by integrating genomic and structural information. Leveraging a Quantum Neural Network (QNN), we classify hotspot mutations, utilizing quantum superposition to uncover intricate relationships within the data. Additionally, a…

Deep learning of thermodynamic laws from microscopic dynamics
Hiroto Kuroyanagi, Tatsuro Yuge
https://arxiv.org/abs/2506.01506 https://

Deep learning of thermodynamic laws from microscopic dynamics
We numerically show that a deep neural network (DNN) can learn macroscopic thermodynamic laws purely from microscopic data. Using molecular dynamics simulations, we generate the data of snapshot images of gas particles undergoing adiabatic processes. We train a DNN to determine the temporal order of input image pairs. We observe that the trained network induces an order relation between states consistent with adiabatic accessibility, satisfying the axioms of thermodynamics. Furthermore, the int…

This https://arxiv.org/abs/2412.07223 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

A Consolidated Volatility Prediction with Back Propagation Neural Network and Genetic Algorithm
This paper provides a unique approach with AI algorithms to predict emerging stock markets volatility. Traditionally, stock volatility is derived from historical volatility,Monte Carlo simulation and implied volatility as well. In this paper, the writer designs a consolidated model with back-propagation neural network and genetic algorithm to predict future volatility of emerging stock markets and found that the results are quite accurate with low errors.

Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control
Zijie Xu, Tong Bu, Zecheng Hao, Jianhao Ding, Zhaofei Yu
https://arxiv.org/abs/2505.24161

Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control
Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision making through neuromorphic hardware, making them compelling for Reinforcement Learning (RL) in resource-constrained edge devices. Recent studies in this field directly replace Artificial Neural Networks (ANNs) by SNNs in existing RL frameworks, overlooking whether the RL algorithm is suitable for SNNs. However, most RL algorithms in continuous control are designed tailored to ANNs, including the target network soft …

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

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

Neural network extraction of chromo-electric and chromo-magnetic gluon masses
Jie Mei, Lingxiao Wang, Mei Huang
https://arxiv.org/abs/2507.22012 https://ar…

Neural network extraction of chromo-electric and chromo-magnetic gluon masses
We present a neural network approach to separate the contributions of chromo-electric and chromo-magnetic gluons within the quasi-particle framework. Using dual residual networks, we extract temperature-dependent masses from SU(3) lattice thermodynamic data of pressure and trace anomaly. After incorporating physics regularizations, the trained models reproduce lattice results with high accuracy over $T/T_c \in [1,10]$, capturing both the crossover behavior near $T_c$ and linear scaling at high …

This https://arxiv.org/abs/2503.02041 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCE_…

Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems
Deep learning has been extensively employed as a powerful function approximator for modeling physics-based problems described by partial differential equations (PDEs). Despite their popularity, standard deep learning models often demand prohibitively large computational resources and yield limited accuracy when scaling to large-scale, high-dimensional physical problems. Their black-box nature further hinders the application in industrial problems where interpretability and high precision are cr…

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

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

Accuracy and Security-Guaranteed Participant Selection and Beamforming Design for RIS-Assisted Federated Learning
Mengru Wu, Yu Gao, Weidang Lu, Huimei Han, Lei Sun, Wanli Ni
https://arxiv.org/abs/2507.00388

Accuracy and Security-Guaranteed Participant Selection and Beamforming Design for RIS-Assisted Federated Learning
Federated learning (FL) has emerged as an effective approach for training neural network models without requiring the sharing of participants' raw data, thereby addressing data privacy concerns. In this paper, we propose a reconfigurable intelligent surface (RIS)-assisted FL framework in the presence of eavesdropping, where partial edge devices are selected to participate in the FL training process. In contrast, the remaining devices serve as cooperative jammers by transmitting jamming signals …

React to Surprises: Stable-by-Design Neural Feedback Control and the Youla-REN
Nicholas H. Barbara, Ruigang Wang, Alexandre Megretski, Ian R. Manchester
https://arxiv.org/abs/2506.01226

React to Surprises: Stable-by-Design Neural Feedback Control and the Youla-REN
We study parameterizations of stabilizing nonlinear policies for learning-based control. We propose a structure based on a nonlinear version of the Youla-Kučera parameterization combined with robust neural networks such as the recurrent equilibrium network (REN). The resulting parameterizations are unconstrained, and hence can be searched over with first-order optimization methods, while always ensuring closed-loop stability by construction. We study the combination of (a) nonlinear dynamics, …

VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration
Shereef Helal, Alberto Garcia-Ortiz, Lennart Bamberg
https://arxiv.org/abs/2506.01166

VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration
Leveraging high degrees of unstructured sparsity is a promising approach to enhance the efficiency of deep neural network DNN accelerators - particularly important for emerging Edge-AI applications. We introduce VUSA, a systolic-array architecture that virtually grows based on the present sparsity to perform larger matrix multiplications with the same number of physical multiply-accumulate MAC units. The proposed architecture achieves saving by 37% and 68% in area and power efficiency, respecti…

M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction
Cunhang Fan, Ying Chen, Jian Zhou, Zexu Pan, Jingjing Zhang, Youdian Gao, Xiaoke Yang, Zhengqi Wen, Zhao Lv
https://arxiv.org/abs/2506.00466

M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction
The brain-assisted target speaker extraction (TSE) aims to extract the attended speech from mixed speech by utilizing the brain neural activities, for example Electroencephalography (EEG). However, existing models overlook the issue of temporal misalignment between speech and EEG modalities, which hampers TSE performance. In addition, the speech encoder in current models typically uses basic temporal operations (e.g., one-dimensional convolution), which are unable to effectively extract target …

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

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

Learning-Based Hybrid Neural Receiver for 6G-V2X Communications
Osama Saleem, Mohammed Alfaqawi, Pierre Merdrignac, Abdelaziz Bensrhair, Soheyb Ribouh
https://arxiv.org/abs/2506.21983

Learning-Based Hybrid Neural Receiver for 6G-V2X Communications
Neural receiver models are proposed to jointly optimize multiple functionalities of wireless receivers; however, a comprehensive receiver model that replaces the entire physical layer blocks has not yet been presented in the literature. In this work, we introduce a novel hybrid neural receiver (H-NR) built on Transformer encoder blocks and Graph Neural Network (GNN), as part of an end-to-end wireless communication framework. In our communication framework, we assume vehicle to network (V2N) upl…

This https://arxiv.org/abs/2505.23425 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hepe…

Hybrid-Graph Neural Network Method for Muon Fast Reconstruction in Neutrino Telescopes
Fast and accurate muon reconstruction is crucial for neutrino telescopes to improve experimental sensitivity and enable online triggering. This paper introduces a Hybrid-Graph Neural Network (GNN) method tailored for efficient muon track reconstruction, leveraging the robustness of GNNs alongside traditional physics-based approaches. The "LITE GNN model" achieves a runtime of 0.19-0.29 ms per event on GPUs, offering a three orders of magnitude speedup compared to traditional likelihood-based me…

Information-theoretic machine learning for time-varying mode decomposition of separated airfoil wakes
Kai Fukami, Ryo Araki
https://arxiv.org/abs/2505.24132

Information-theoretic machine learning for time-varying mode decomposition of separated airfoil wakes
We perform an information-theoretic mode decomposition for separated wakes around a wing. The current data-driven approach based on a neural network referred to as deep sigmoidal flow enables the extraction of an informative component from a given flow field snapshot with respect to a target variable at a future time stamp, thereby capturing the causality as a time-varying modal structure. We consider three examples of separated flows around a NACA0012 airfoil, namely, 1. laminar periodic wake …

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
@…

This https://arxiv.org/abs/2505.05532 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Design and FPGA Implementation of WOMBAT: A Deep Neural Network Level-1 Trigger System for Jet Substructure Identification and Boosted $H\rightarrow b\bar{b}$ Tagging at the CMS Experiment
This thesis investigates the physics performance, trigger efficiency, and Field Programmable Gate Array (FPGA) implementation of machine learning (ML)-based algorithms for Lorentz-boosted $H\rightarrow b\bar{b}$ tagging within the CMS Level-1 Trigger (L1T) under Phase-1 conditions. The proposed algorithm, WOMBAT (Wide Object ML Boosted Algorithm Trigger), comprises a high-performance Master Model (W-MM) and a quantized, FPGA-synthesizable Apprentice Model (W-AM), benchmarked against the standar…

Automated Vehicles Should be Connected with Natural Language
Xiangbo Gao, Keshu Wu, Hao Zhang, Kexin Tian, Yang Zhou, Zhengzhong Tu
https://arxiv.org/abs/2507.01059

Automated Vehicles Should be Connected with Natural Language
Multi-agent collaborative driving promises improvements in traffic safety and efficiency through collective perception and decision making. However, existing communication media -- including raw sensor data, neural network features, and perception results -- suffer limitations in bandwidth efficiency, information completeness, and agent interoperability. Moreover, traditional approaches have largely ignored decision-level fusion, neglecting critical dimensions of collaborative driving. In this …

Iola Walker: A Mobile Footfall Detection System for Music Composition
Will James
https://arxiv.org/abs/2506.01211 https://arxiv.org/p…

Iola Walker: A Mobile Footfall Detection System for Music Composition
This project is the first of several experiments composing music that changes in response to biosignals. The system is dubbed "iola walker" in reference to a common polyrhythm, the hemiola. A listener goes for a walk, and the Iola Walker app detects their walking pace. Iola Walker picks up footfalls using a foot-mounted accelerometer, processing the signals in real time using a recurrent neural network in an Android app. The Android app outputs a MIDI event for each footfall. The iola walker pl…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/4]:
- Fully Differentiable Lagrangian Convolutional Neural Network for Physics-Informed Precipitation N...
Peter Pavl\'ik, Martin V\'yboh, Anna Bou Ezzeddine, Viera Rozinajov\'a

Refining Czech GEC: Insights from a Multi-Experiment Approach
Petr Pechman, Milan Straka, Jana Strakov\'a, Jakub N\'aplava
https://arxiv.org/abs/2506.22402

Refining Czech GEC: Insights from a Multi-Experiment Approach
We present a grammar error correction (GEC) system that achieves state of the art for the Czech language. Our system is based on a neural network translation approach with the Transformer architecture, and its key feature is its real-time synthetic generation pipeline, which dynamically augments sentences with artificial errors by introducing both language-agnostic and Czech-specific errors. We conduct a comprehensive series of experiments, investigating the Czech GEC corpora as bases for synth…

Adaptive Neural Quantum States: A Recurrent Neural Network Perspective
Jake McNaughton, Mohamed Hibat-Allah
https://arxiv.org/abs/2507.18700 https://arxiv.…

Adaptive Neural Quantum States: A Recurrent Neural Network Perspective
Neural-network quantum states (NQS) are powerful neural-network ansätzes that have emerged as promising tools for studying quantum many-body physics through the lens of the variational principle. These architectures are known to be systematically improvable by increasing the number of parameters. Here we demonstrate an Adaptive scheme to optimize NQSs, through the example of recurrent neural networks (RNN), using a fraction of the computation cost while reducing training fluctuations and impro…

From Large-scale Audio Tagging to Real-Time Explainable Emergency Vehicle Sirens Detection
Stefano Giacomelli, Marco Giordano, Claudia Rinaldi, Fabio Graziosi
https://arxiv.org/abs/2506.23437

From Large-scale Audio Tagging to Real-Time Explainable Emergency Vehicle Sirens Detection
Accurate recognition of Emergency Vehicle (EV) sirens is critical for the integration of intelligent transportation systems, smart city monitoring systems, and autonomous driving technologies. Modern automatic solutions are limited by the lack of large scale, curated datasets and by the computational demands of state of the art sound event detection models. This work introduces E2PANNs (Efficient Emergency Pre trained Audio Neural Networks), a lightweight Convolutional Neural Network architectu…

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

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

Neural network enabled wide field-of-view imaging with hyperbolic metalenses
Joel Yeo, Deepak K. Sharma, Saurabh Srivastava, Aihong Huang, Emmanuel Lassalle, Egor Khaidarov, Keng Heng Lai, Yuan Hsing Fu, N. Duane Loh, Ramon Paniagua-Dominguez, Arseniy I. Kuznetsov
https://arxiv.org/abs/2507.21562

Neural network enabled wide field-of-view imaging with hyperbolic metalenses
The ultrathin form factor of metalenses makes them highly appealing for novel sensing and imaging applications. Amongst the various phase profiles, the hyperbolic metalens stands out for being free from spherical aberrations and having one of the highest focusing efficiencies to date. For imaging, however, hyperbolic metalenses present significant off-axis aberrations, severely restricting the achievable field-of-view (FOV). Extending the FOV of hyperbolic metalenses is thus feasible only if th…

Energy-Embedded Neural Solvers for One-Dimensional Quantum Systems
Yi-Qiang Wu, Xuan Liu, Hanlin Li, Fuqiang Wang
https://arxiv.org/abs/2505.24194 https://…

Energy-Embedded Neural Solvers for One-Dimensional Quantum Systems
Physics-informed neural networks (PINN) have been widely used in computational physics to solve partial differential equations (PDEs). In this study, we propose an energy-embedding-based physics-informed neural network method for solving the one-dimensional time-independent Schrödinger equation to obtain ground- and excited-state wave functions, as well as energy eigenvalues by incorporating an embedding layer to generate process-driven data. The method demonstrates high accuracy for several w…

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

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

Unraveling Open Quantum Dynamics with Time-Dependent Variational Monte Carlo
Christian Apostoli, Jacopo D'Alberto, Marco G. Genoni, Gianluca Bertaina, Davide E. Galli
https://arxiv.org/abs/2506.23928

Unraveling Open Quantum Dynamics with Time-Dependent Variational Monte Carlo
We introduce a method to simulate open quantum many-body dynamics by combining time-dependent variational Monte Carlo (tVMC) with quantum trajectory techniques. Our approach unravels the Lindblad master equation into an ensemble of stochastic Schrödinger equations for a variational ansatz, avoiding the exponential cost of density matrix evolution. The method is compatible with generic ansatzë, including expressive neural-network wavefunctions. We derive the nonlinear stochastic equations of m…

Parameter-Free Bio-Inspired Channel Attention for Enhanced Cardiac MRI Reconstruction
Anam Hashmi, Julia Dietlmeier, Kathleen M. Curran, Noel E. O'Connor
https://arxiv.org/abs/2505.23872

Parameter-Free Bio-Inspired Channel Attention for Enhanced Cardiac MRI Reconstruction
Attention is a fundamental component of the human visual recognition system. The inclusion of attention in a convolutional neural network amplifies relevant visual features and suppresses the less important ones. Integrating attention mechanisms into convolutional neural networks enhances model performance and interpretability. Spatial and channel attention mechanisms have shown significant advantages across many downstream tasks in medical imaging. While existing attention modules have proven …

Replaced article(s) found for cs.NE. https://arxiv.org/list/cs.NE/new
[1/1]:
- Benchmarking Spiking Neural Network Learning Methods with Varying Locality
Jiaqi Lin, Sen Lu, Malyaban Bal, Abhronil Sengupta

A Novel Discrete Memristor-Coupled Heterogeneous Dual-Neuron Model and Its Application in Multi-Scenario Image Encryption
Yi Zou, Mengjiao Wang, Xinan Zhang, Herbert Ho-Ching Iu
https://arxiv.org/abs/2505.24294

A Novel Discrete Memristor-Coupled Heterogeneous Dual-Neuron Model and Its Application in Multi-Scenario Image Encryption
Simulating brain functions using neural networks is an important area of research. Recently, discrete memristor-coupled neurons have attracted significant attention, as memristors effectively mimic synaptic behavior, which is essential for learning and memory. This highlights the biological relevance of such models. This study introduces a discrete memristive heterogeneous dual-neuron network (MHDNN). The stability of the MHDNN is analyzed with respect to initial conditions and a range of neuro…

FMIP: Multimodal Flow Matching for Mixed Integer Linear Programming
Hongpei Li, Hui Yuan, Han Zhang, Dongdong Ge, Mengdi Wang, Yinyu Ye
https://arxiv.org/abs/2507.23390 https://…

FMIP: Multimodal Flow Matching for Mixed Integer Linear Programming
Mixed-Integer Linear Programming (MILP) is a cornerstone of mathematical optimization, enabling the modeling of complex decision-making problems involving both integer and continuous variables. Despite its versatility, most MILP problems are NP-complete, making them challenging to solve in practice. Existing graph neural network (GNN)-based heuristics aim to reduce problem scale by predicting only the solutions on integer variables for a given instance, struggling to capture the intricate inter…

Rapid yet accurate Tile-circuit and device modeling for Analog In-Memory Computing
J. Luquin, C. Mackin, S. Ambrogio, A. Chen, F. Baldi, G. Miralles, M. J. Rasch, J. B\"uchel, M. Lalwani, W. Ponghiran, P. Solomon, H. Tsai, G. W. Burr, P. Narayanan
https://arxiv.org/abs/2506.00004

Rapid yet accurate Tile-circuit and device modeling for Analog In-Memory Computing
Analog In-Memory Compute (AIMC) can improve the energy efficiency of Deep Learning by orders of magnitude. Yet analog-domain device and circuit non-idealities -- within the analog ``Tiles'' performing Matrix-Vector Multiply (MVM) operations -- can degrade neural-network task accuracy. We quantify the impact of low-level distortions and noise, and develop a mathematical model for Multiply-ACcumulate (MAC) operations mapped to analog tiles. Instantaneous-current IR-drop (the most significant circ…

This https://arxiv.org/abs/2505.15304 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control
Deep neural network (DNN)-based policy models, such as vision-language-action (VLA) models, excel at automating complex decision-making from multi-modal inputs. However, scaling these models greatly increases computational overhead, complicating deployment in resource-constrained settings like robot manipulation and autonomous driving. To address this, we propose Saliency-Aware Quantized Imitation Learning (SQIL), which combines quantization-aware training with a selective loss-weighting strate…

This https://arxiv.org/abs/2410.00059 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Method
Illegitimate reproduction, distribution and derivation of Deep Neural Network (DNN) models can inflict economic loss, reputation damage and even privacy infringement. Passive DNN intellectual property (IP) protection methods such as watermarking and fingerprinting attempt to prove the ownership upon IP violation, but they are often too late to stop catastrophic damage of IP abuse and too feeble against strong adversaries. In this paper, we propose IDEA, an Inverse Domain Expert Adaptation based…

A holomorphic Kolmogorov-Arnold network framework for solving elliptic problems on arbitrary 2D domains
Matteo Calaf\`a, Tito Andriollo, Allan P. Engsig-Karup, Cheol-Ho Jeong
https://arxiv.org/abs/2507.22678

A holomorphic Kolmogorov-Arnold network framework for solving elliptic problems on arbitrary 2D domains
Physics-informed holomorphic neural networks (PIHNNs) have recently emerged as efficient surrogate models for solving differential problems. By embedding the underlying problem structure into the network, PIHNNs require training only to satisfy boundary conditions, often resulting in significantly improved accuracy and computational efficiency compared to traditional physics-informed neural networks (PINNs). In this work, we improve and extend the application of PIHNNs to two-dimensional proble…

This https://arxiv.org/abs/2504.11918 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Deep learning to improve the discovery of near-Earth asteroids in the Zwicky Transient Facility
We present a novel pipeline that uses a convolutional neural network (CNN) to improve the detection capability of near-Earth asteroids (NEAs) in the context of planetary defense. Our work aims to minimize the dependency on human intervention of the current approach adopted by the Zwicky Transient Facility (ZTF). The target NEAs have a high proper motion of up to tens of degrees per day and thus appear as streaks of light in the images. We trained our CNNs to detect these streaks using three dat…

Reconstruction of Partial Dissimilarity Matrices for Cognitive Neuroscience
Denise Moerel, Tijl Grootswagers
https://arxiv.org/abs/2506.00484 https://

Reconstruction of Partial Dissimilarity Matrices for Cognitive Neuroscience
In cognitive neuroscience research, Representational Dissimilarity Matrices (RDMs) are often incomplete because pairwise similarity judgments cannot always be exhaustively collected as the number of pairs rapidly increases with the number of conditions. Existing methods to fill these missing values, such as deep neural network imputation, are powerful but computationally demanding and relatively opaque. We introduce a simple algorithm based on geometric inference that fills missing dissimilarit…

Hybrid tensor network and neural network quantum states for quantum chemistry
Zibo Wu, Bohan Zhang, Wei-Hai Fang, Zhendong Li
https://arxiv.org/abs/2507.19276 https://

Hybrid tensor network and neural network quantum states for quantum chemistry
Neural network quantum states (NQS) have emerged as a powerful and flexible framework for addressing quantum many-body problems. While successful for model Hamiltonians, their application to molecular systems remains challenging for several reasons. In this work, we introduce three innovations to overcome some of the key limitations. (1) We propose two novel ansätzet hat hybridize tensor network and neural network states for addressing initialization challenges and enhancing the expressivity o…

Confidence intervals for forced alignment boundaries using model ensembles
Matthew C. Kelley
https://arxiv.org/abs/2506.01256 https://

Confidence intervals for forced alignment boundaries using model ensembles
Forced alignment is a common tool to align audio with orthographic and phonetic transcriptions. Most forced alignment tools provide only a single estimate of a boundary. The present project introduces a method of deriving confidence intervals for these boundaries using a neural network ensemble technique. Ten different segment classifier neural networks were previously trained, and the alignment process is repeated with each model. The alignment ensemble is then used to place the boundary at th…

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

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

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

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

AirCANS: CFD 2D Mesh Optimisation-based Airfoil Classification and Assessment using Neural Networks
Lushun Fan, Yuqin Xia, Jun Li, Karl Jenkins
https://arxiv.org/abs/2506.22662

AirCANS: CFD 2D Mesh Optimisation-based Airfoil Classification and Assessment using Neural Networks
This study explores the possibilities of automating the loading, classification and assessment of Computational Fluid Dynamics (CFD) mesh data by Convolutional Neural Networks (CNNs). The research aim is finding a feasible way to quickly make classification and assessment on airfoil mesh data. For this purpose, this study designed a new framework named CFD-based airfoil Classification and Assessment Network (AirCANS) for CFD mesh data which including the data loader and improved the CNN structu…

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…

This https://arxiv.org/abs/2504.21841 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Neuro-Symbolic Generation of Explanations for Robot Policies with Weighted Signal Temporal Logic
Neural network-based policies have demonstrated success in many robotic applications, but often lack human-explanability, which poses challenges in safety-critical deployments. To address this, we propose a neuro-symbolic explanation framework that generates a weighted signal temporal logic (wSTL) specification to describe a robot policy in a interpretable form. Existing methods typically produce explanations that are verbose and inconsistent, which hinders explainability, and loose, which do n…

This https://arxiv.org/abs/2311.16139 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models
Graph Neural Networks (GNNs) have become indispensable tools for learning from graph structured data, catering to various applications such as social network analysis and fraud detection for financial services. At the heart of these networks are the edges, which are crucial in guiding GNN models' predictions. In many scenarios, these edges represent sensitive information, such as personal associations or financial dealings, which require privacy assurance. However, their contributions to GNN mo…

Real-Time Emergency Vehicle Siren Detection with Efficient CNNs on Embedded Hardware
Marco Giordano, Stefano Giacomelli, Claudia Rinaldi, Fabio Graziosi
https://arxiv.org/abs/2507.01563

Real-Time Emergency Vehicle Siren Detection with Efficient CNNs on Embedded Hardware
We present a full-stack emergency vehicle (EV) siren detection system designed for real-time deployment on embedded hardware. The proposed approach is based on E2PANNs, a fine-tuned convolutional neural network derived from EPANNs, and optimized for binary sound event detection under urban acoustic conditions. A key contribution is the creation of curated and semantically structured datasets - AudioSet-EV, AudioSet-EV Augmented, and Unified-EV - developed using a custom AudioSet-Tools framework…

PINN and GNN-based RF Map Construction for Wireless Communication Systems
Lizhou Liu, Xiaohui Chen, Zihan Tang, Mengyao Ma, Wenyi Zhang
https://arxiv.org/abs/2507.22513 https://…

PINN and GNN-based RF Map Construction for Wireless Communication Systems
Radio frequency (RF) map is a promising technique for capturing the characteristics of multipath signal propagation, offering critical support for channel modeling, coverage analysis, and beamforming in wireless communication networks. This paper proposes a novel RF map construction method based on a combination of physics-informed neural network (PINN) and graph neural network (GNN). The PINN incorporates physical constraints derived from electromagnetic propagation laws to guide the learning …

Hardware acceleration for ultra-fast Neural Network training on FPGA for MRF map reconstruction
Mattia Ricchi, Fabrizio Alfonsi, Camilla Marella, Marco Barbieri, Alessandra Retico, Leonardo Brizi, Alessandro Gabrielli, Claudia Testa
https://arxiv.org/abs/2506.22156

Hardware acceleration for ultra-fast Neural Network training on FPGA for MRF map reconstruction
Magnetic Resonance Fingerprinting (MRF) is a fast quantitative MR Imaging technique that provides multi-parametric maps with a single acquisition. Neural Networks (NNs) accelerate reconstruction but require significant resources for training. We propose an FPGA-based NN for real-time brain parameter reconstruction from MRF data. Training the NN takes an estimated 200 seconds, significantly faster than standard CPU-based training, which can be up to 250 times slower. This method could enable rea…

Predicting Parkinson's Disease Progression Using Statistical and Neural Mixed Effects Models: A Comparative Study on Longitudinal Biomarkers
Ran Tong, Lanruo Wang, Tong Wang, Wei Yan
https://arxiv.org/abs/2507.20058

Predicting Parkinson's Disease Progression Using Statistical and Neural Mixed Effects Models: A Comparative Study on Longitudinal Biomarkers
Predicting Parkinson's Disease (PD) progression is crucial, and voice biomarkers offer a non-invasive method for tracking symptom severity (UPDRS scores) through telemonitoring. Analyzing this longitudinal data is challenging due to within-subject correlations and complex, nonlinear patient-specific progression patterns. This study benchmarks LMMs against two advanced hybrid approaches: the Generalized Neural Network Mixed Model (GNMM) (Mandel 2021), which embeds a neural network within a GLMM …

HMPC-assisted Adversarial Inverse Reinforcement Learning for Smart Home Energy Management
Jiadong He, Liang Yu, Zhiqiang Chen, Dawei Qiu, Dong Yue, Goran Strbac, Meng Zhang, Yujian Ye, Yi Wang
https://arxiv.org/abs/2506.00898

HMPC-assisted Adversarial Inverse Reinforcement Learning for Smart Home Energy Management
This letter proposes an Adversarial Inverse Reinforcement Learning (AIRL)-based energy management method for a smart home, which incorporates an implicit thermal dynamics model. In the proposed method, historical optimal decisions are first generated using a neural network-assisted Hierarchical Model Predictive Control (HMPC) framework. These decisions are then used as expert demonstrations in the AIRL module, which aims to train a discriminator to distinguish expert demonstrations from transit…

Variational PINNs with tree-based integration and boundary element data in the modeling of multi-phase architected materials
Dimitrios C. Rodopoulos, Panos Pantidis, Nikolaos Karathanasopoulos
https://arxiv.org/abs/2506.23357

Variational PINNs with tree-based integration and boundary element data in the modeling of multi-phase architected materials
The current contribution develops a Variational Physics-Informed Neural Network (VPINN)-based framework for the analysis and design of multiphase architected solids. The elaborated VPINN methodology is based on the Petrov-Galerkin approach, with a deep neural network acting as trial function and local polynomials as test functions. For the analysis, a Galerkin Boundary Element Method (GBEM) scheme is developed to generate the mechanical field data, employing solely domain boundary information. …

Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
D. Veerababu, Ashwin A. Raikar, Prasanta K. Ghosh
https://arxiv.org/abs/2507.21749

Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
Training neural networks can be challenging, especially as the complexity of the problem increases. Despite using wider or deeper networks, training them can be a tedious process, especially if a wrong choice of the hyperparameter is made. The learning rate is one of such crucial hyperparameters, which is usually kept static during the training process. Learning dynamics in complex systems often requires a more adaptive approach to the learning rate. This adaptability becomes crucial to effecti…

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge
Nabarun Goswami, Tatsuya Harada
https://arxiv.org/abs/2506.00809

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge
We propose a multi-stage framework for universal speech enhancement, designed for the Interspeech 2025 URGENT Challenge. Our system first employs a Sparse Compression Network to robustly separate sources and extract an initial clean speech estimate from noisy inputs. This is followed by an efficient generative model that refines speech quality by leveraging self-supervised features and optimizing a masked language modeling objective on acoustic tokens derived from a neural audio codec. In the f…

Hybrid-Graph Neural Network Method for Muon Fast Reconstruction in Neutrino Telescopes
Cen Mo, Liang Li
https://arxiv.org/abs/2505.23425 https://

Hybrid-Graph Neural Network Method for Muon Fast Reconstruction in Neutrino Telescopes
Fast and accurate muon reconstruction is crucial for neutrino telescopes to improve experimental sensitivity and enable online triggering. This paper introduces a Hybrid-Graph Neural Network (GNN) method tailored for efficient muon track reconstruction, leveraging the robustness of GNNs alongside traditional physics-based approaches. The "LITE GNN model" achieves a runtime of 0.19-0.29 ms per event on GPUs, offering a three orders of magnitude speedup compared to traditional likelihood-based me…

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

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

Quantum-Cognitive Tunnelling Neural Networks for Military-Civilian Vehicle Classification and Sentiment Analysis
Milan Maksimovic, Anna Bohdanets, Immaculate Motsi-Omoijiade, Guido Governatori, Ivan S. Maksymov
https://arxiv.org/abs/2507.18645

Quantum-Cognitive Tunnelling Neural Networks for Military-Civilian Vehicle Classification and Sentiment Analysis
Prior work has demonstrated that incorporating well-known quantum tunnelling (QT) probability into neural network models effectively captures important nuances of human perception, particularly in the recognition of ambiguous objects and sentiment analysis. In this paper, we employ novel QT-based neural networks and assess their effectiveness in distinguishing customised CIFAR-format images of military and civilian vehicles, as well as sentiment, using a proprietary military-specific vocabulary…

Bi-Residual Neural Network based Synchronous Motor Electrical Faults Diagnosis: Intra-link Layer Design for High-frequency Features
Qianchao Wang, Leena Heistrene, Yoash Levron, Yuxuan Ding, Yaping Du
https://arxiv.org/abs/2505.23097

Bi-Residual Neural Network based Synchronous Motor Electrical Faults Diagnosis: Intra-link Layer Design for High-frequency Features
In practical resource-constrained environments, efficiently extracting the potential high-frequency fault-critical information is an inherent problem. To overcome this problem, this work suggests leveraging a bi-residual neural network named Bi-ResNet to extract the inner spatial-temporal high-frequency features using embedded spatial-temporal convolution blocks and intra-link layers. It can be considered as embedding a high-frequency extractor into networks without adding any parameters, helpi…

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

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

Physics-informed neural network framework for solving forward and inverse flexoelectric problems
Hyeonbin Moon, Donggeun Park, Jinwook Yeo, Seunghwa Ryu
https://arxiv.org/abs/2506.21810

Physics-informed neural network framework for solving forward and inverse flexoelectric problems
Flexoelectricity, the coupling between strain gradients and electric polarization, poses significant computational challenges due to its governing fourth-order partial differential equations that require C1-continuous solutions. To address these issues, we propose a physics-informed neural network (PINN) framework grounded in an energy-based formulation that treats both forward and inverse problems within a unified architecture. The forward problem is recast as a saddle-point optimization of th…

Of Good Demons and Bad Angels: Guaranteeing Safe Control under Finite Precision
Samuel Teuber, Debasmita Lohar, Bernhard Beckert
https://arxiv.org/abs/2507.22760 https://…

Of Good Demons and Bad Angels: Guaranteeing Safe Control under Finite Precision
As neural networks (NNs) become increasingly prevalent in safety-critical neural network-controlled cyber-physical systems (NNCSs), formally guaranteeing their safety becomes crucial. For these systems, safety must be ensured throughout their entire operation, necessitating infinite-time horizon verification. To verify the infinite-time horizon safety of NNCSs, recent approaches leverage Differential Dynamic Logic (dL). However, these dL-based guarantees rely on idealized, real-valued NN semant…

Flexible Mixed Precision Quantization for Learned Image Compression
Md Adnan Faisal Hossain, Zhihao Duan, Fengqing Zhu
https://arxiv.org/abs/2506.01221 htt…

Flexible Mixed Precision Quantization for Learned Image Compression
Despite its improvements in coding performance compared to traditional codecs, Learned Image Compression (LIC) suffers from large computational costs for storage and deployment. Model quantization offers an effective solution to reduce the computational complexity of LIC models. However, most existing works perform fixed-precision quantization which suffers from sub-optimal utilization of resources due to the varying sensitivity to quantization of different layers of a neural network. In this p…

A Novel Post-Quantum Secure Digital Signature Scheme Based on Neural Network
Satish Kumar, Md. Arzoo Jamal
https://arxiv.org/abs/2507.20676 https://arxiv.o…

A Novel Post-Quantum Secure Digital Signature Scheme Based on Neural Network
Digital signatures are fundamental cryptographic primitives that ensure the authenticity and integrity of digital documents. In the post-quantum era, classical public key-based signature schemes become vulnerable to brute-force and key-recovery attacks due to the computational power of quantum algorithms. Multivariate polynomial based signature schemes are among the one of the cryptographic constructions that offers strong security guarantees against such quantum threats. With the growing capab…

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

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

Local Stability and Region of Attraction Analysis for Neural Network Feedback Systems under Positivity Constraints
Hamidreza Montazeri Hedesh, Moh Kamalul Wafi, Milad Siami
https://arxiv.org/abs/2505.22889

Local Stability and Region of Attraction Analysis for Neural Network Feedback Systems under Positivity Constraints
We study the local stability of nonlinear systems in the Lur'e form with static nonlinear feedback realized by feedforward neural networks (FFNNs). By leveraging positivity system constraints, we employ a localized variant of the Aizerman conjecture, which provides sufficient conditions for exponential stability of trajectories confined to a compact set. Using this foundation, we develop two distinct methods for estimating the Region of Attraction (ROA): (i) a less conservative Lyapunov-based a…

Keyed Chaotic Tensor Transformations for Secure And Attributable Neural Inference
Peter David Fagan
https://arxiv.org/abs/2505.23655 https://

Keyed Chaotic Tensor Transformations for Secure And Attributable Neural Inference
This work introduces a novel framework for secure and privacy-preserving neural network inference based on keyed chaotic dynamical transformations. The proposed method applies a deterministic, cryptographically seeded chaotic system to tensors, producing non-invertible, user-specific transformations that enable authenticated inference, tensor-level watermarking, and data attribution. This framework offers a scalable and lightweight alternative to conventional cryptographic techniques, and estab…

Physics-Informed Neural Networks with Dynamical Boundary Constraints
Andr\'es Mart\'inez-Esteban, Pablo Calvo-Barl\'es, Luis Mart\'in-Moreno, Sergio G Rodrigo
https://arxiv.org/abs/2507.21800

Physics-Informed Neural Networks with Dynamical Boundary Constraints
Physics-informed neural networks (PINNs) are numerical solvers that embed all the physical information of a system into the loss function of a neural network. In this way the learned solution accounts for data (if available), the governing differential equations, or any other constraint known of the physical problem. However, they face serious issues, notably their tendency to converge on trivial or misleading solutions. The latter occurs when, although the loss function reaches low values the …

Benchmarking Universal Machine Learning Interatomic Potentials for Real-Time Analysis of Inelastic Neutron Scattering Data
Bowen Han, Yongqiang Cheng
https://arxiv.org/abs/2506.01860

Benchmarking Universal Machine Learning Interatomic Potentials for Real-Time Analysis of Inelastic Neutron Scattering Data
The accurate calculation of phonons and vibrational spectra remains a significant challenge, requiring highly precise evaluations of interatomic forces. Traditional methods based on the quantum description of the electronic structure, while widely used, are computationally expensive and demand substantial expertise. Emerging universal machine learning interatomic potentials (uMLIPs) offer a transformative alternative by employing pre-trained neural network surrogates to predict interatomic forc…

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

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