Browse by author
Lookup NU author(s): Dr Colin Tosh
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
Artificial neural networks are becoming increasingly popular as predictive statistical tools in ecosystem ecology and as models of signal processing in behavioural and evolutionary ecology. We demonstrate here that a commonly used network in ecology, the three-layer feed-forward network, trained with the backpropagation algorithm, can be extremely sensitive to the stochastic variation in training data that results from random sampling of the same underlying statistical distribution, with networks converging to several distinct predictive states. Using a random walk procedure to sample error–weight space, and Sammon dimensional reduction of weight arrays, we demonstrate that these different predictive states are not artefactual, due to local minima, but lie at the base of major error troughs in the error–weight surface. We further demonstrate that various gross weight compositions can produce the same predictive state, suggesting the analogy of weight space as a ‘patchwork’ of multiple predictive states. Our results argue for increased inclusion of stochastic training replication and analysis into ecological and behavioural applications of artificial neural networks.
Author(s): Tosh CR, Ruxton GD
Publication type: Article
Publication status: Published
Journal: Philosophical Transactions of the Royal Society, B: Biological Sciences
Year: 2007
Volume: 362
Issue: 1479
Pages: 455-460
ISSN (print): 0962-8452
ISSN (electronic): 1471-2954
Publisher: Royal Society Publishing
URL: http://dx.doi.org/10.1098/rstb.2006.1973
DOI: 10.1098/rstb.2006.1973
Altmetrics provided by Altmetric
