XOR has no local minima

A case study in neural network error surface analysis

Leonard G C Hamey*

*Corresponding author for this work

Research output: Contribution to journalArticle

40 Citations (Scopus)


This paper presents a case study of the analysis of local minima in feedforward neural networks. Firstly, a new methodology for analysis is presented, based upon consideration of trajectories through weight space by which a training algorithm might escape a hypothesized local minimum. This analysis method is then applied to the well known XOR (exclusive-or) problem, which has previously been considered to exhibit local minima. The analysis proves the absence of local minima, eliciting significant aspects of the structure of the error surface. The present work is important for the study of the existence of local minima in feedforward neural networks, and also for the development of training algorithms which avoid or escape entrapment in local minima.

Original languageEnglish
Pages (from-to)669-681
Number of pages13
JournalNeural Networks
Issue number4
Publication statusPublished - Jun 1998


  • Error surface
  • Exclusive-or
  • Feedforward nets
  • Local minimum
  • XOR

Fingerprint Dive into the research topics of 'XOR has no local minima: A case study in neural network error surface analysis'. Together they form a unique fingerprint.

Cite this