A weight initialization based on the linear product structure for neural networks

DOI10.1016/j.amc.2021.126722OpenAlexW3205063073MaRDI QIDQ2247166

Juncai He, Qipin Chen, Wenrui Hao

Publication date: 16 November 2021

Published in: Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2109.00125

zbMATH Keywords

neural networksnonlinear computationlinear product structureweight initialization

Mathematics Subject Classification ID

Numerical analysis (65-XX) Probabilistic methods, stochastic differential equations (65Cxx) Nonlinear algebraic or transcendental equations (65Hxx)

Related Items (2)

Side effects of learning from low-dimensional data embedded in a Euclidean space ⋮ Global exponential stability for delayed Clifford-valued coupled neural networks with impulsive effects

Uses Software

• Bertini
• MNIST
• CIFAR
• ImageNet
• Adam

Cites Work

• Unnamed Item
• A gradient descent method for solving a system of nonlinear equations
• An adaptive homotopy method for computing bifurcations of nonlinear parametric systems
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• A homotopy training algorithm for fully connected neural networks
• Dying ReLU and Initialization: Theory and Numerical Examples
• The Numerical Solution of Systems of Polynomials Arising in Engineering and Science

This page was built for publication: A weight initialization based on the linear product structure for neural networks