Article
Mutation-based genetic neural network.
IEEE transactions on neural networks - 1 May 2005
Palmes Paulito P, Hayasaka Taichi, Usui Shiro
Abstract excerpt
Evolving gradient-learning artificial neural networks (ANNs) using an evolutionary algorithm (EA) is a popular approach to address the local optima and design problems of ANN. The typical approach is to combine the strength of backpropagation (BP) in weight learning and EA's capability of searching the architecture space. However, the BP's "gradient descent" approach requires a highly computer-intensive operation...
Read the complete abstract on PubMedTopics
Share this publication in a Topic to start or enrich a Post.
