arxivAug 3

Freeze, Then Select: Structured Field Adapters and Stability-Validated Weak Selection for PDE Discovery from Sparse Observations

arXiv:2607.29665v1 Announce Type: new Abstract: PDE discovery from sparse observations requires reconstructing a continuous field and selecting the correct differential terms. Our analysis of optimization paths in coupled neural PDE discovery reveals three behaviors: the exact support can persist to

#pde-discovery #neural-networks #machine-learning Read on arxiv →

arxivAug 3

A Hamiltonian driven Geometric Construction of Neural Networks via the Lognormal family, Application to Financial Fraud Detection and to Network Security

arXiv:2509.25778v3 Announce Type: replace Abstract: We presents a method for constructing neural networks intrinsically on statistical manifolds via the lognormal distribution. We demonstrate this approach by formulating a neural network architecture directly on statistical manifold. The constructio

#neural-networks #statistical-manifolds #machine-learning Read on arxiv →

arxivJul 31

Optimizing Sensor Placement for Hydrogen Leak Detection in Enclosed Infrastructure: A Comparative Study Using CFD-informed Genetic Algorithm and DeepSets Neural Surrogate

arXiv:2607.26078v1 Announce Type: cross Abstract: Hydrogen infrastructure in enclosed environments, such as parking facilities for fuel cell vehicles, presents significant safety challenges due to hydrogen's low ignition energy and wide flammability range. Current monitoring systems are largely reac

DE1 model #safety #optimization #neural-networks Read on arxiv →

arxivJul 31bullish

MLVC: Multi-platform Learned Video Codec for Real-World Deployment

arXiv:2606.28027v2 Announce Type: replace-cross Abstract: Neural video codecs have surpassed classical codecs in coding efficiency but remain impractical for deployment due to cross-platform incompatibility and high computational cost. Existing quantization-based solutions fail to produce determinis

MLDC2 models #video-codecs #cross-platform #neural-networks Read on arxiv →

arxivJul 30

Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?

arXiv:2607.25529v1 Announce Type: new Abstract: As neural network models for image classification advance, neurons play critical roles in pruning, backdoor defense, and interpretability. Yet existing work lacks clarity on the weight-importance relationship. We address this with a neuron importance a

#neural-networks #image-classification #interpretability Read on arxiv →

arxivJul 30bullish

Amortized Moment Matching for Visual Generation

arXiv:2607.26860v1 Announce Type: new Abstract: We propose amortized moment matching, utilizing neural networks to learn data moments as distributional training signals. By casting diffusion denoisers through polynomial projections, we establish a general framework for moment amortization, revealing

#machine-learning #generative-models #neural-networks Read on arxiv →

arxivJul 24

Error Amplification Limits ANN-to-SNN Conversion in Continuous Control

arXiv:2601.21778v3 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) can achieve competitive performance by converting already existing well-trained Artificial Neural Networks (ANNs), avoiding further costly training. This property is particularly attractive in Reinforcement Lear

#neural-networks #reinforcement-learning #conversion Read on arxiv →

arxivJul 22bullish

SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions

arXiv:2607.18290v1 Announce Type: cross Abstract: In recent years, Kolmogorov-Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scientific computing tasks, offering a new paradigm for neural network design. In this paper, we present SechKAN

SEMU2 models #machine-learning #neural-networks #scientific-computing Read on arxiv →

arxivJul 20bullish

Evolutionary Algorithm-Guided LLMs for Physics-Informed Neural Network Design

arXiv:2607.15560v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) are unusually sensitive to interacting choices of architecture, activation, loss weighting, collocation, optimization, and constraint enforcement. Large language models (LLMs) can propose these choices, but in

PILL2 models #neural-networks #evolutionary-algorithm #optimization Read on arxiv →

arxivJul 16

A Shared Subcircuit Lets LLMs Count Down Across Tasks

arXiv:2607.12279v1 Announce Type: new Abstract: Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an ASCII table. These are all tasks that language models can do that requires tracking how many tokens remain before a target. In this work, we identify in

ME1 model #language-models #research #neural-networks Read on arxiv →

arxivJul 3bullish

Efficient Temporal Point Processes via Monotone Alternating Splines

arXiv:2607.01752v1 Announce Type: new Abstract: Temporal point processes (TPPs) have widespread applications across various domains. Compared to modeling the conditional intensity of a TPP, modeling its cumulative conditional intensity function (CCIF) improves computational efficiency and eliminates

MOMO2 models #machine-learning #temporal-point-processes #neural-networks Read on arxiv →

arxivJun 24

Activation Functions, Statistics and Learning of Higher-Order Interactions in Restricted Boltzmann Machines

arXiv:2605.19178v2 Announce Type: replace-cross Abstract: The great success of neural networks primarily arises from the presence of the large number of weight parameters combined with nonlinearities in the input-output relationship of single neurons. In this work, we study the relationship between

RE1 model #neural-networks #machine-learning #statistical-mechanics Read on arxiv →

arxivJun 5

Binary Spiking Neural Networks as Causal Models

arXiv:2604.27007v2 Announce Type: replace Abstract: We provide a causal analysis of Binary Spiking Neural Networks (BSNNs) to explain their behavior. We formally define a BSNN and represent its spiking activity as a binary causal model. Thanks to this causal representation, we are able to explain th

BI1 model #explainability #neural-networks #causal-analysis Read on arxiv →

arxivJun 2

How Much Orthogonalization Does Muon Need?

arXiv:2606.00371v1 Announce Type: new Abstract: Muon optimizers improve neural-network training by replacing ill-conditioned momentum updates with approximately semi-orthogonal updates. This motivates a practical question: how much orthogonalization does Muon actually require? We study this question

NAGPMA4 models · +1 #machine-learning #optimization #neural-networks Read on arxiv →

arxivJun 1bullish

Evolutionary Algorithm for Reservoir Learning and Yielding

arXiv:2605.30372v1 Announce Type: cross Abstract: Reservoir computing, a type of recurrent neural network, is a promising approach for temporal learning as it separates dynamic processing from the trained readout layer. However, classical Echo State Networks (ESNs) often require task-specific tuning

ECEA2 models #neural-networks #evolutionary-computing #temporal-learning Read on arxiv →

arxivMay 28bullish

Learning Compositional Latent Structure with Vector Networks

arXiv:2605.28007v1 Announce Type: cross Abstract: Deep networks are powerful function approximators, but they typically store many different computations in shared weight matrices, making it difficult to selectively reuse or adapt parts of them when a familiar structure appears in novel combinations

VE1 model #machine-learning #artificial-intelligence #neural-networks Read on arxiv →

arxivMay 26bullish

Kolmogorov-Arnold Fourier Networks

arXiv:2502.06018v3 Announce Type: replace-cross Abstract: Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical expressiveness, they suffer from severe parameter explosion and limited ability to capture high-frequency features in high-dimensional tasks. To address

KO1 model #machine-learning #neural-networks #spectral-reparameterization Read on arxiv →

arxivMay 18

Rethinking Neural Network Learning Rates: A Stackelberg Perspective

arXiv:2605.15530v1 Announce Type: new Abstract: Neural networks are typically trained with a single learning rate across all layers. While recent empirical evidence suggests that assigning layer-specific learning rates can accelerate training, a principled understanding of the conditions and mechani

#machine-learning #optimization #neural-networks Read on arxiv →

arxivMay 16

Numerical exploration of the range of shape functionals using neural networks

arXiv:2602.14881v2 Announce Type: replace-cross Abstract: We introduce a novel numerical framework for the exploration of Blaschke--Santal\'o diagrams, which are efficient tools characterizing the possible inequalities relating some given shape functionals. We introduce a parametrization of convex b

IN1 model #optimization #neural-networks #geometry Read on arxiv →

arxivMay 6

A Synthesizable RTL Implementation of Predictive Coding Networks

arXiv:2603.18066v2 Announce Type: replace-cross Abstract: Backpropagation has enabled modern deep learning but is difficult to realize as an online, fully distributed hardware learning system due to global error propagation, phase separation, and heavy reliance on centralized memory. Predictive codi

#hardware #predictive-coding #neural-networks Read on arxiv →

arxivApr 30

A Multi-Dataset Benchmark of Multiple Instance Learning for 3D Neuroimage Classification

arXiv:2604.26807v1 Announce Type: new Abstract: Despite being resource-intensive to train, 3D convolutional neural networks (CNNs) have been the standard approach to classify CT and MRI scans. Recent work suggests that deep multiple instance learning (MIL) may be a more efficient alternative for 3D

3D3DMI3 models #medical-imaging #neural-networks #efficiency Read on arxiv →

arxivApr 27bullish

HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference

arXiv:2604.22293v1 Announce Type: cross Abstract: Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitives. However, state-of-the-art LUT-aware training (LAT) approaches remai

HG1 model #hardware #efficiency #neural-networks Read on arxiv →

arxivApr 24bullish

Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks

arXiv:2305.01626v4 Announce Type: replace-cross Abstract: Computational models of syntax are predominantly text-based. Here we propose that the most basic first step in the evolution of syntax can be modeled directly from raw speech in a fully unsupervised way. We focus on one of the most ubiquitous

CIFICN3 models #speech-processing #neural-networks #language-modeling Read on arxiv →

arxivApr 15

On the Convergence Analysis of Muon

arXiv:2505.23737v2 Announce Type: replace-cross Abstract: The majority of parameters in neural networks are naturally represented as matrices. However, most commonly used optimizers treat these matrix parameters as flattened vectors during optimization, potentially overlooking their inherent structu

MUGR2 models #optimization #neural-networks #machine-learning Read on arxiv →

arxivApr 14bullish

MSTN: A Lightweight and Fast Model for General TimeSeries Analysis

arXiv:2511.20577v3 Announce Type: replace Abstract: Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary architect

MUMSMS3 models #time-series #neural-networks #forecasting Read on arxiv →

arxivApr 13bullish

Boosting Brain-inspired Path Integration Efficiency via Learning-based Replication of Continuous Attractor Neurodynamics

arXiv:2511.17687v2 Announce Type: replace Abstract: The brain's Path Integration (PI) mechanism offers substantial guidance and inspiration for Brain-Inspired Navigation (BIN). However, the PI capability constructed by the Continuous Attractor Neural Networks (CANNs) in most existing BIN studies exh

COAR2 models #machine-learning #neural-networks #navigation Read on arxiv →

arxivApr 10

Introducing Echo Networks for Computational Neuroevolution

arXiv:2604.08204v1 Announce Type: new Abstract: For applications on the extreme edge, minimal networks of only a few dozen artificial neurons for event detection and classification in discrete time signals would be highly desirable. Feed-forward networks, RNNs, and CNNs evolved through evolutionary

ECNERN4 models · +1 #machine-learning #neural-networks #evolutionary-computing Read on arxiv →

arxivApr 9

Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study

arXiv:2512.19253v3 Announce Type: replace-cross Abstract: We present the first empirical study of machine unlearning (MU) in hybrid quantum-classical neural networks. While MU has been extensively explored in classical deep learning, its behavior within variational quantum circuits (VQCs) and quantu

#machine-learning #quantum-computing #neural-networks Read on arxiv →

arxivApr 9bullish

Graph Neural ODE Digital Twins for Control-Oriented Reactor Thermal-Hydraulic Forecasting Under Partial Observability

arXiv:2604.07292v1 Announce Type: new Abstract: Real-time supervisory control of advanced reactors requires accurate forecasting of plant-wide thermal-hydraulic states, including locations where physical sensors are unavailable. Meeting this need calls for surrogate models that combine predictive fi

GRNE2 models #physics-informed #neural-networks #real-time Read on arxiv →