On Random Matrices Arising in Deep Neural Networks. Gaussian Case

zbMath1467.15032arXiv2001.06188MaRDI QIDQ4992247

Leonid Pastur

Publication date: 7 June 2021

Full work available at URL: https://arxiv.org/abs/2001.06188

zbMATH Keywords

random matricesdeep neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Random matrices (probabilistic aspects) (60B20) Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Eigenvalues, singular values, and eigenvectors (15A18) Random matrices (algebraic aspects) (15B52)

Related Items (6)

Eigenvalue distribution of large random matrices arising in deep neural networks: Orthogonal case ⋮ Large-dimensional random matrix theory and its applications in deep learning and wireless communications ⋮ Linear eigenvalue statistics of XX′ matrices ⋮ The Law of Multiplication of Large Random Matrices Revisited ⋮ A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent* ⋮ Universal characteristics of deep neural network loss surfaces from random matrix theory

This page was built for publication: On Random Matrices Arising in Deep Neural Networks. Gaussian Case