This paper develops a novel, computationally efficient method to quantify the uncertainty in wide neural network predictions by characterizing the limiting random fluctuations using stochastic evoluti…

This paper establishes an exact mathematical correspondence between training and inference in deep learning and the solution of Hamilton-Jacobi partial differential equations, unifying multiple theore…

The paper introduces an adaptive reservoir computing framework that tailors Echo State Networks (ESNs) to specific evaluation scenarios, achieving a high score on the CTF-4-Science Lorenz benchmark fo…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

The paper introduces a unified Physics-Informed Deep Learning (PIDL) framework that simultaneously enforces physical laws and information-theoretic bounds, demonstrating robust, domain-agnostic entrop…

This paper analyzes the computational complexity of verifying feedforward neural networks when their weights are restricted to finite-width arithmetic, finding that verification remains NP-complete fo…

The paper formalizes the problem of representation identifiability in supervised learning, showing that a representation property is identifiable if and only if it is constant across all possible fact…

The paper introduces and analyzes several novel data appraisal metrics, including the Vendi Score and matrix spectral functions, demonstrating that efficient optimization techniques make these metrics…

This study empirically benchmarks classical and quantum machine learning models for image recognition, finding that while quantum models offer superior accuracy and resource efficiency at high dimensi…

The paper proposes a novel information-geometric framework to analyze LLM stability by integrating task utility, external entropy, and internal structural proxies, showing this composite score improve…

The scaling exponent in neural scaling laws is not fixed but systematically depends on the optimizer used, with preconditioned optimizers generally yielding steeper scaling.

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…

This study compares multiple post-hoc explainable AI methods (e.g., DeepSHAP, GradCAM) to interpret how deep learning models use EEG data to detect Major Depressive Disorder, finding that while method…

This paper develops a framework for conformal prediction in dyadic regression problems under complex missingness mechanisms.

This paper develops a framework for conformal prediction in dyadic regression problems under complex missingness mechanisms.

The paper proposes two novel multi-column RBFN architectures, MC-PSO and MC-APSO, that combine parallel RBFN structures with swarm optimization to significantly outperform existing methods in accuracy…

The paper introduces Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) to achieve massive, structured compression of deep neural networks, demonstrating compression ratios up to 77,000x…

The paper introduces an Equilibrium Propagation (EP)-based training method for Predictive Coding Networks (PCNs), successfully training a large-scale VGG10 model on ImageNet and achieving state-of-the…