neural activation function

基本解釋

Method: Based on dynamic error correction BP artificial neural network with Hyperbolic Tangent function as activation function and the number of hidden node six.
方法：利用動態(tài)學習比率BP算法以雙曲正切函數(shù)爲功能函數(shù)的非線性時間序列預測方法。
Methods Based on dynamic error correction BP using artificial neural network with Hyperbolic Tangent function as activation function and the number of hidden node six.
方法利用動態(tài)學習比率BP算法以雙曲正切函數(shù)爲功能函數(shù)的非線性時間序列預測方法。
BP algorithm is often used to correct weights of neural network because number of hidden nodes, studying speed and generation ability of neural network are related to activation function.
以往的BP算法調(diào)節(jié)神經(jīng)元網(wǎng)絡的權值，其網(wǎng)絡的隱層結點數(shù)、網(wǎng)絡學習快慢程度及網(wǎng)絡的泛化能力都與網(wǎng)絡的激勵函數(shù)有關的。