Lesson 20 神經(jīng)網(wǎng)絡簡介
神經(jīng)網(wǎng)絡(Artificial Neural Network)
全程為人工神經(jīng)網(wǎng)絡,是一種模仿生物神經(jīng)網(wǎng)絡的結(jié)構(gòu)和功能的非線性統(tǒng)計數(shù)據(jù)模型
Sigmoid函數(shù)是最簡單的神經(jīng)網(wǎng)絡模型

Neural Network
API小結(jié):
mpcModel = MLPClassifier(
hidden_layer_sizes, activation='relu'
)
#hidden_layer_sizes: 隱藏層層數(shù)
#activation: 激活函數(shù)栅干,默認為relu
activation激活函數(shù)
- relu: 線性糾正函數(shù)迈套,優(yōu)于logistics和tanh
- logistic: logistic 函數(shù)
- tahn: tahn函數(shù) tanh(x)=2sigmoid(2x)?1
sigmoid_vs_tahn.png