Training Neural Networks with an algorithm for piecewise linear functions

Francisco Barahona, João N. C. Gonçalves

Publication date: 13 May 2021

Abstract: We present experiments on training neural networks with an algorithm that was originally designed as a subgradient method, namely the Volume Algorithm. We compare with two of the most frequently used algorithms like Momentum and Adam. We also compare with the newly proposed algorithm COCOB.

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

This page was built for publication: Training Neural Networks with an algorithm for piecewise linear functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6367614)