New algorithm to investigate neural networks

DOI10.1016/0010-4655(96)00086-0MaRDI QIDQ1294638zbMATHOpenAlexFDO

Authors B. Berg

Publication date 26 April 2000

Published in Computer Physics Communications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/hep-ph/9604207

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonnumerical algorithms (68W05)

Abstract: Random cost simulations were introduced as a method to investigate optimization problems in systems with conflicting constraints. Here I study the approach in connection with the training of a feed-forward multilayer perceptron, as used in high energy physics applications. It is suggested to use random cost simulations for generating a set of selected configurations. On each of those final minimization may then be performed by a standard algorithm. For the training example at hand many almost degenerate local minima are thus found. Some effort is spend to discuss whether they lead to equivalent classifications of the data.

Cites work

• scientific article; zbMATH DE number 41029 (Why is no real title available?)
• Optimization by simulated annealing

Cited in

(1)

• Signal confidence limits from a neural network data analysis

This page was built for publication: New algorithm to investigate neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1294638)