Informatics Report Series



Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Title:Developing complex systems using evolved pattern generators
Authors: James Bednar ; R. Miikkulainen ; V. Valsalam
Date:Apr 2007
Publication Title:IEEE Transactions on Evolutionary Computation
Publication Type:Journal Article Publication Status:Published
Volume No:11 (2) Page Nos:181-198
DOI:10.1109/TEVC.2006.890272 ISBN/ISSN:1089-778X
Self-organization of connection patterns within brain areas of animals begins prenatally, and has been shown to depend on internally generated patterns of neural activity. The neural structures continue to develop postnatally through externally driven patterns, when the sensory systems are exposed to stimuli from the environment. The internally generated patterns have been proposed to give the neural system an appropriate bias so that it can learn reliably from complex environmental stimuli. This paper evaluates the hypothesis that complex artificial learning systems can benefit from a similar approach, consisting of initial training with patterns from an evolved pattern generator, followed by training with the actual training set. To test this hypothesis, competitive learning networks were trained for recognizing handwritten digits. The results demonstrate how the approach can improve learning performance by discovering the appropriate initial weight biases, thereby compensating for weaknesses of the learning algorithm, Due to the smaller evolutionary search space, this approach was also found to require much fewer generations than direct evolution network weights. Since discovering the right biases efficiently is critical for solving large-scale problems with learning, these results suggest that internal training pattern generation is an effective method for sconstructing complex systems.
Links To Paper
No links available
Bibtex format
author = { James Bednar and R. Miikkulainen and V. Valsalam },
title = {Developing complex systems using evolved pattern generators},
journal = {IEEE Transactions on Evolutionary Computation},
publisher = {IEEE},
year = 2007,
month = {Apr},
volume = {11 (2)},
pages = {181-198},
doi = {10.1109/TEVC.2006.890272},

Home : Publications : Report 

Please mail <> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh