The Principles of Deep Learning Theory

DOI10.1017/9781009023405zbMath1507.68003arXiv2106.10165OpenAlexW3176723190WikidataQ113991308 ScholiaQ113991308MaRDI QIDQ5070199

Daniel A. Roberts, Sho Yaida

Publication date: 11 April 2022

Full work available at URL: https://arxiv.org/abs/2106.10165

zbMATH Keywords

neural networksrenormalization grouprepresentation theoryneural tangent kernelnearly-Gaussian distributions

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Introductory exposition (textbooks, tutorial papers, etc.) pertaining to computer science (68-01)

Related Items (7)

Unified field theoretical approach to deep and recurrent neuronal networks ⋮ Asymptotics of representation learning in finite Bayesian neural networks* ⋮ Inferring parameters of pyramidal neuron excitability in mouse models of Alzheimer's disease using biophysical modeling and deep learning ⋮ Random neural networks in the infinite width limit as Gaussian processes ⋮ \(p\)-adic statistical field theory and deep belief networks ⋮ On random matrices arising in deep neural networks: General I.I.D. case ⋮ -Stable convergence of heavy-/light-tailed infinitely wide neural networks

This page was built for publication: The Principles of Deep Learning Theory