Design Multilayer Feed-forward Networks Based on Immune Evolutionary Programming

The authors use an immune evolutionary programming to design multilayer feed-forward networksin this paper. The immune evolutionary programming retains the ability of stochastic global searching of tradi-tional evolutionary programming, and draws into the interaction mechanism based on density and the diversitymaintaining mechanism which exists in living beings' immune procedure, The immune evolutionary program-ming has better global convergence and very strong self-adaptive ability with enviornment. The experimentalresults prove the high efficiency of the immune evolutionary programming in designing neural networks.