Optimization of neural network weights and architectures for odor recognition using simulated annealing
A Yamazaki, MCP De Souto… - Proceedings of the 2002 …, 2002 - ieeexplore.ieee.org
A Yamazaki, MCP De Souto, TB Ludermir
Proceedings of the 2002 International Joint Conference on Neural …, 2002•ieeexplore.ieee.orgShows results of using simulated annealing for optimizing neural network architectures and
weights. The algorithm generates networks with good generalization performance (mean
classification error of 5.28%) and low complexity (mean number of connections of 11.68 out
of 36) for an odor recognition task in an artificial nose.
weights. The algorithm generates networks with good generalization performance (mean
classification error of 5.28%) and low complexity (mean number of connections of 11.68 out
of 36) for an odor recognition task in an artificial nose.
Shows results of using simulated annealing for optimizing neural network architectures and weights. The algorithm generates networks with good generalization performance (mean classification error of 5.28%) and low complexity (mean number of connections of 11.68 out of 36) for an odor recognition task in an artificial nose.
ieeexplore.ieee.org