Using SOM for Neural Network Visualization

Authors:
Gustavo Romero;Pedro A. Castillo Valdivieso;Juan J. Merelo Guervós;Alberto Prieto
Affiliations:
-;-;-;-
Venue:
IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Year:
2001

Citing 3
Cited 0

Pattern Recognition and Neural Networks

Pattern Recognition and Neural Networks
Evolutionary Computation Visualization: Application to G-PROP

PPSN VI Proceedings of the 6th International Conference on Parallel Problem Solving from Nature
A Nonlinear Mapping for Data Structure Analysis

IEEE Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

Soft ware visualization is an area of computer science deoted to supporting the understanding and effective use of algorithms. The application of soft ware visualization to Evolutionary Conputation has been receiving increasing technique to an evolutionary algorithm for multilayer preceptron training. Our goal is to better understand its internal behavior in order to improve the evolutionary part of the method. The effect of several genetic operators are compare and the difference with a fitness sharing version of the algorithm.