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(dòng)態(tài)學(xué)習(xí)比率BP算法以雙曲正切函數(shù)爲(wèi)功能函數(shù)的非線(xiàn)性時(shí)間序列預(yù)測(cè)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(dòng)態(tài)學(xué)習(xí)比率BP算法以雙曲正切函數(shù)爲(wèi)功能函數(shù)的非線(xiàn)性時(shí)間序列預(yù)測(cè)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(luò)的權(quán)值，其網(wǎng)絡(luò)的隱層結(jié)點(diǎn)數(shù)、網(wǎng)絡(luò)學(xué)習(xí)快慢程度及網(wǎng)絡(luò)的泛化能力都與網(wǎng)絡(luò)的激勵(lì)函數(shù)有關(guān)的。