Ensemble Techniques for Avoiding Poor Performance in Evolved Neural Networks

— The idea of using evolutionary techniques to optimize the performance of neural networks is now widely used, but some approaches have been found to result in the evolution of risky learning strategies that lead to occasional instances of very poor performance. In this paper I shall present a series of simulations that explore the nature of those problems, and examine the extent to which one can use ensemble techniques to alleviate them.

• Type: Conference
• Year: 2006
• Where: IJCNN
• Authors: John A. Bullinaria
• Keywords: Evolutionary Techniques, IJCNN 2006, Neural Networks, Risky Learning Strategies