Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?

DOI10.1109/TSP.2016.2546221zbMath1414.94217arXiv1504.08291OpenAlexW1625958017MaRDI QIDQ4619648

Guillermo Sapiro, Alex M. Bronstein, Raja Giryes

Publication date: 7 February 2019

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1504.08291

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items (11)

Eigenvalue distribution of large random matrices arising in deep neural networks: Orthogonal case ⋮ Numerical bifurcation analysis of PDEs from lattice Boltzmann model simulations: a parsimonious machine learning approach ⋮ A random matrix approach to neural networks ⋮ Compressive statistical learning with random feature moments ⋮ Approximation Analysis of Convolutional Neural Networks ⋮ On random matrices arising in deep neural networks: General I.I.D. case ⋮ Simple Classification using Binary Data ⋮ Eigenvalue distribution of some nonlinear models of random matrices ⋮ Entropy and mutual information in models of deep neural networks* ⋮ Unnamed Item ⋮ Unnamed Item

This page was built for publication: Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?