Image de couverture de livre

Deep neural networks from the perspective of ergodic theory

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Zhang, Fan
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Disordered Systems and Neural Networks
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Emergent weight morphologies in deep neural networks
par: de Jong, Pascal, et autres
Publié: (2025)

High-dimensional learning of narrow neural networks
par: Cui, Hugo
Publié: (2024)

Finite-time Lyapunov exponents of deep neural networks
par: Storm, L., et autres
Publié: (2023)

Supervised and Unsupervised protocols for hetero-associative neural networks
par: Alessandrelli, Andrea, et autres
Publié: (2025)

Computing frustration and near-monotonicity in deep neural networks
par: Wendin, Joel, et autres
Publié: (2025)

Adaptive kernel predictors from feature-learning infinite limits of neural networks
par: Lauditi, Clarissa, et autres
Publié: (2025)

Training neural networks with structured noise improves classification and generalization
par: Benedetti, Marco, et autres
Publié: (2023)

How does training shape the Riemannian geometry of neural network representations?
par: Zavatone-Veth, Jacob A., et autres
Publié: (2023)

Spring-block theory of feature learning in deep neural networks
par: Shi, Cheng, et autres
Publié: (2024)

Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networks
par: D'Amico, Francesco, et autres
Publié: (2025)

Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective
par: Ghio, Davide, et autres
Publié: (2023)

Boundary between noise and information applied to filtering neural network weight matrices
par: Staats, Max, et autres
Publié: (2022)

Universal characteristics of deep neural network loss surfaces from random matrix theory
par: Baskerville, Nicholas P, et autres
Publié: (2022)

Statistical physics analysis of graph neural networks: Approaching optimality in the contextual stochastic block model
par: Duranthon, O., et autres
Publié: (2025)

Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations
par: Baldassi, Carlo, et autres
Publié: (2019)

Towards a theory of how the structure of language is acquired by deep neural networks
par: Cagnetta, Francesco, et autres
Publié: (2024)

Solution space and storage capacity of fully connected two-layer neural networks with generic activation functions
par: Nishiyama, Sota, et autres
Publié: (2024)

Injectivity of ReLU networks: perspectives from statistical physics
par: Maillard, Antoine, et autres
Publié: (2023)

Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
par: Huang, Jie, et autres
Publié: (2026)

Pruning-induced phases in fully-connected neural networks: the eumentia, the dementia, and the amentia
par: Pan, Haining, et autres
Publié: (2026)

A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights
par: Ricci, Fabiola, et autres
Publié: (2026)

New non-Euclidean neural quantum states from additional types of hyperbolic recurrent neural networks
par: Dao, H. L.
Publié: (2026)

Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks
par: Annesi, Brandon L., et autres
Publié: (2024)

What can we learn from quantum convolutional neural networks?
par: Umeano, Chukwudubem, et autres
Publié: (2023)

Coding schemes in neural networks learning classification tasks
par: van Meegen, Alexander, et autres
Publié: (2024)

Applying statistical learning theory to deep learning
par: Gerbelot, Cédric, et autres
Publié: (2023)

Asymptotic theory of in-context learning by linear attention
par: Lu, Yue M., et autres
Publié: (2024)

On the role of non-linear latent features in bipartite generative neural networks
par: Bonnaire, Tony, et autres
Publié: (2025)

Field theory for optimal signal propagation in ResNets
par: Fischer, Kirsten, et autres
Publié: (2023)

A unified theory of feature learning in RNNs and DNNs
par: Bauer, Jan P., et autres
Publié: (2026)

A universal approximation theorem for nonlinear resistive networks
par: Scellier, Benjamin, et autres
Publié: (2023)

A solvable model of learning generative diffusion: theory and insights
par: Cui, Hugo, et autres
Publié: (2025)

A universal compression theory for lottery ticket hypothesis and neural scaling laws
par: Wang, Hong-Yi, et autres
Publié: (2025)

The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems
par: Biazzo, Indaco
Publié: (2023)

Homophily modulates double descent generalization in graph convolution networks
par: Shi, Cheng, et autres
Publié: (2022)

Self-attention as an attractor network: transient memories without backpropagation
par: D'Amico, Francesco, et autres
Publié: (2024)

The twin peaks of learning neural networks
par: Demyanenko, Elizaveta, et autres
Publié: (2024)

Asymptotic generalization error of a single-layer graph convolutional network
par: Duranthon, O., et autres
Publié: (2024)

Learning curves theory for hierarchically compositional data with power-law distributed features
par: Cagnetta, Francesco, et autres
Publié: (2025)

A simple theory for training response of deep neural networks
par: Nakazato, Kenichi
Publié: (2024)