|
|
STRUCTURAL OPTIMIZATION OF MULTILAYER FEEDFORWARD NETWORKS BASED ON EVOLUTIONARY PROGRAMMING |
Li Ying①; Bai Bendu②; Jiao Licheng① |
①Key Lab for Radar Signal Processing Xidian Universitij Xi' an 710071 China;②Xidian University Xi'an 710071 China |
|
|
Abstract Based on evolutionary programming, a novel algorithm named EPANN for designing the topology and weight distributions of feedforward networks is proposed in this paper. EPANN algorithm evolves network architectures and connection weights (including biases) simultaneously and emphasizes the behavioral links between parents and their offspring in evolution, such as weights training after each architectural mutation and node splitting. Unlike the pure constructive or pruning algorithm, EPANN's architectural mutations include both node
deletion and node addition, and prefer node deletion to addition in order to encourage the network architecture as compact as possible and generalization ability as good as possible.
|
Received: 30 November 1999
|
|
|
|
|
|
|
|