Arctangent Activation Function to Accelerate Backpropagation Learning

スポンサーリンク

概要

• 論文の詳細を見る

• One of the reasons of slow convergence in Backpropagation learning is the diminishing value of the derivative of the commonly used activation functions as the nodes approach extreme values, namely, 0 or ±1. In this letter, we propose arctangent activation function to accelerate learning speed. Simulation results indicate considerable improvement in convergence performance.

• 社団法人電子情報通信学会の論文
• 2002-10-01

著者

• Kamruzzaman Joarder

  Faculty Of Information Technology Monash University

関連論文

• Application of Support Vector Machine to Forex Monitoring
• Improving Convergence of Backpropagation Learning using Exponential Cost Function
• Arctangent Activation Function to Accelerate Backpropagation Learning

スポンサーリンク