Abstract | ||
---|---|---|
This contribution offers an experimental study of the influence of learning on evolution in populations bf neural networks in which evolutionary and learning fitness surfaces are set and known in advance. Although not biologically plausible, this allows us to investigate various hypotheses regarding the interaction between evolution and learning in neural networks, such as "neighbourhood correlation" and "relearning", in easily controled conditions. Experimental results are presented comparing the evolution of neural networks, with and without learning and on similar and dissimilar tasks. The results chart the evolutionary progress of neural network populations in terms of fitness at birth and fitness after lifetime learning on the different tasks presented and with different selection pressures. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1109/ICSMC.1998.725017 | 1998 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5 |
Keywords | Field | DocType |
genetic algorithms(26A0), neural networks(25A0), machine learning(35A0) | Evolutionary acquisition of neural topologies,Competitive learning,Evolutionary robotics,Computer science,Recurrent neural network,Types of artificial neural networks,Artificial intelligence,Deep learning,Artificial neural network,Machine learning,Learning classifier system | Conference |
ISSN | Citations | PageRank |
1062-922X | 0 | 0.34 |
References | Authors | |
0 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Brian Carse | 1 | 259 | 26.31 |