The structure of neural network error surfaces

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

Abstract

Analysis of the error surfaces of feed-forward neural networks is complicated by the high dimensionality of the weight space. Visualisation over one- and two-dimensional slices, and Monte Carlo analysis of stationary points can produce misleading results. We show that, in some situations, important features of the error surface can only be visualised by considering the error over non-planar manifolds of weight space. We also show that Monte Carlo simulations can depend critically upon the random step size chosen. The relationship can reveal key properties of the local structure of the error surface.
Original languageEnglish
Title of host publicationProceedings of the Sixth Australian Conference on Neural Networks
EditorsM Charles, C Latimer
Place of PublicationSydney
PublisherThe University of Sydney
Pages197-200
Number of pages4
ISBN (Print)0909391033
Publication statusPublished - 1995

    Fingerprint

Cite this

Hamey, L. (1995). The structure of neural network error surfaces. In M. Charles, & C. Latimer (Eds.), Proceedings of the Sixth Australian Conference on Neural Networks (pp. 197-200). Sydney: The University of Sydney.