[2606.00157] Interpreting FCDNNs via RG on Exponential Family
Abstract page for arXiv paper 2606.00157: Interpreting FCDNNs via RG on Exponential Family
America Forever Bytes
Other
Abstract page for arXiv paper 2606.00157: Interpreting FCDNNs via RG on Exponential Family
Abstract page for arXiv paper 2606.01244: Efficient Approximation for Encoder--Decoder Neural Operators via Variation Spaces
Abstract page for arXiv paper 2606.02292: Neural Acquisition & Representation of Subsurface Scattering
Abstract page for arXiv paper 2606.01442: On the Evaluation of Spiking Neural Network Configurations for Network Intrusion Detection
Abstract page for arXiv paper 2605.30456: DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
Abstract page for arXiv paper 2605.30944: Neural-network excited states of $A=4$ nuclei and hypernuclei
Abstract page for arXiv paper 2508.11911: Reduced-order modeling of Hamiltonian dynamics based on symplectic neural networks
Abstract page for arXiv paper 2605.31244: Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
Abstract page for arXiv paper 2605.30659: Neural-Network-based Viscosity Closure for Non-Newtonian Multiphase Flows
Abstract page for arXiv paper 2605.31299: Memristor-Based Spiking Neural Network Accelerator for Bio-inspired Interception Task
Abstract page for arXiv paper 2605.31106: Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural Networks
Abstract page for arXiv paper 2605.31022: Augmented Lagrangian Predictive Coding
Abstract page for arXiv paper 2605.31027: Multi-Scale Separable Fourier Neural Networks for Solving High-Frequency PDEs
Abstract page for arXiv paper 2508.09925: Residual Reservoir Memory Networks
Abstract page for arXiv paper 2605.30361: Gradient-Free Training of Spiking Neural Networks via Low-Rank Evolution Strategies
Abstract page for arXiv paper 2605.30362: XOResNet: Exclusive-OR Meta-Residuals Facilitate Deep Spiking Neural Networks Learning
Abstract page for arXiv paper 2605.30370: Updating the standard neuron model in artificial neural networks
From having gone down a wikipedia rabbit hole from hyperdimensional computing I ended up making a programming language that is quite different from p…
Abstract page for arXiv paper 2507.21429: From Sublinear to Linear: Local Convergence in Finite-Width Networks via Locally Polyak-Lojasiewicz Regions
Abstract page for arXiv paper 2605.29211: Tail observability and fourth-order closure recovery in physics-informed neural networks for Bhatnagar-Gross-Krook nor...
Abstract page for arXiv paper 2605.29537: The Complexity of Verifying Feedforward Neural Networks in Quantised Settings
Abstract page for arXiv paper 2605.27568: Solitonic Construction of Artificial Neural Networks from Nonlinear Field Theory
Abstract page for arXiv paper 2605.28291: Dual Variational Neural Network for the $p$-Laplace Problem
Abstract page for arXiv paper 2605.27411: Genetic algorithm vs. gradient descent for training a neural network architecture dedicated to low data regimes in sma...
Abstract page for arXiv paper 2605.27412: Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradients
Abstract page for arXiv paper 2605.27467: Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, an...
Abstract page for arXiv paper 2605.27569: RULER: Representation-Level Verification of Machine Unlearning
Abstract page for arXiv paper 2605.28149: Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations
Abstract page for arXiv paper 2403.09441: Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency