Informatics Report Series



Related Pages

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

Title:Constructing good learners using evolved pattern generators.
Authors: Vinod Valsalam ; James Bednar ; Risto Miikkulainen
Date: 2005
Publication Title:Proceedings of GECCO 2005 (Genetic and Evolutionary Computation Conference)
Publication Type:Conference Paper Publication Status:Published
Page Nos:11-18
Self-organization of brain areas in animals begins prenatally, evidently driven by spontaneously generated internal patterns. The neural structures continue to develop postnatally when the sensory systems are exposed to stimuli from the environment. In this process, prenatal training may give the neural system the appropriate bias so that it can learn reliably under changing environmental stimuli. This paper evaluates the hypothesis that an artificial learning system can benefit from a similar approach, consisting of initial training with patterns from an evolved generator followed by training with the actual training set. Competitive learning networks were trained in recognizing handwritten digits in three ways: through environmental learning only, through evolution only, and through prenatal training with evolved pattern generators followed by environmental learning. The results demonstrate that the evolved pattern generator approach leads to better learning performance, suggesting that complex systems can be constructed effectively in this way.
Links To Paper
1st Link
2nd Link
Bibtex format
author = { Vinod Valsalam and James Bednar and Risto Miikkulainen },
title = {Constructing good learners using evolved pattern generators.},
book title = {Proceedings of GECCO 2005 (Genetic and Evolutionary Computation Conference)},
publisher = {ACM},
year = 2005,
pages = {11-18},
doi = {10.1145/1068009.1068012},
url = {},

Home : Publications : Report 

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