Title :
Evolution and design of distributed learning rules
Author :
Runarsson, Thomas Philip ; Jonsson, Magnus Thor
Author_Institution :
Dept. of Mech. Eng., Iceland Univ., Reykjavik, Iceland
Abstract :
The paper describes the application of neural networks as learning rules for the training of neural networks. The learning rule is part of the neural network architecture. As a result the learning rule is non-local and globally distributed within the network. The learning rules are evolved using an evolution strategy. The survival of a learning rule is based on its performance in training neural networks on a set of tasks. Training algorithms will be evolved for single layer artificial neural networks. Experimental results show that a learning rule of this type is very capable of generating an efficient training algorithm
Keywords :
evolutionary computation; learning (artificial intelligence); neural nets; distributed learning rule evolution; evolution strategy; experimental results; neural network architecture; neural network training; rule performance; single layer neural networks; Animals; Artificial neural networks; Biological neural networks; Evolution (biology); Genetic algorithms; Learning; Mechanical engineering; Neural networks; Neurons; Stochastic processes;
Conference_Titel :
Combinations of Evolutionary Computation and Neural Networks, 2000 IEEE Symposium on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-6572-0
DOI :
10.1109/ECNN.2000.886220