Toggle Main Menu Toggle Search

Open Access padlockePrints

The need for stochastic replication of ecological neural networks

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.

Publication metadata

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


DOI: 10.1098/rstb.2006.1973


Altmetrics provided by Altmetric


Find at Newcastle University icon    Link to this publication