Averaged learning equations of error-function-based multilayer perceptrons

作者：Guo Weili^*; Wei Haikun; Zhao Junsheng; Zhang Kanjian

来源：Neural Computing & Applications, 2014, 25(3-4): 825-832.

DOI：10.1007/s00521-014-1557-5

• Averaged learning equation
• Multilayer perceptrons
• Error function
• Singularity

The multilayer perceptrons (MLPs) have strange behaviors in the learning process caused by the existing singularities in the parameter space. A detailed theoretical or numerical analysis of the MLPs is difficult due to the non-integrability of the traditional log-sigmoid activation function which leads to difficulties in obtaining the averaged learning equations (ALEs). In this paper, the error function is suggested as the activation function of the MLPs. By solving the explicit expressions of two important expectations, we obtain the averaged learning equations which make it possible for further analysis of the learning dynamics in MLPs. The simulation results also indicate that the ALEs play a significant role in investigating the singular behaviors of MLPs.

• 出版日期2014-9
• 单位东南大学; 聊城大学