VII Brazilian Symposium on Neural Networks (SBRN'02) Global Optimization Methods for Designing and Training Neural Networks Pernambuco, Brazil November 11-November 14 ISBN: 0-7695-1709-9
This paper shows results of two approaches for the optimization of neural networks: one uses simulated annealing for optimizing both architectures and weights combined with backpropagation for fine tuning, while the other uses tabu search for the same purpose. Both approaches generate networks with good generalization performance (mean classification error of 1.68% for simulated annealing and 0.64% for tabu search) and low complexity (mean number of connections of 11.15 out of 36 for simulated annealing and 11.62 out of 36 for tabu search) for an odor recognition task in an artificial nose.
Citation:
Akio Yamazaki, Teresa B. Ludermir, Marcílio C.P. de Souto, "Global Optimization Methods for Designing and Training Neural Networks," sbrn, pp.136, VII Brazilian Symposium on Neural Networks (SBRN'02), 2002 Usage of this product signifies your acceptance of the Terms of Use. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb