A New Chaotic Neural Network Algorithm for "0-1" Optimization Problems Based Non-monotonous Activation Function

作者：Wang Xiuhong^*; Qiao Qingli

来源：International Conference on Artificial Intelligence and Computational Intelligence (AICI 2012), 2012-10-26 to 2012-10-28.

• Chaotic neural network
• Non-monotonous Activation Function
• 0-1 optimization problem

"0-1"optimization problems are special cases of the integer programming, and are commonly encountered in many optimization problems. In this paper, a new transiently chaotic neural network model with non-monotonous activation function for solving "0-1"optimization problem has been presented. In order to have higher ability of overcoming drawbacks that suffered from the local minimum and converge to the optimal solution quickly, a hysteretic activation function which is multi-valued, adaptive, and has memory is used in the proposed model. Numerical simulation of 0-1 optimization problem shows that the proposed model has higher ability to search for globally optimal and has higher searching efficiency in solving the "0-1"optimization problems.

• 出版日期2012
• 单位天津大学