流程
code
import numpy as np
# 定義tanh函數
def tanh(x):
return np.tanh(x)
# tanh函數的導數
def tan_deriv(x):
return 1.0 - np.tanh(x) * np.tan(x)
# sigmoid函數
def logistic(x):
return 1 / (1 + np.exp(-x))
# sigmoid函數的導數
def logistic_derivative(x):
return logistic(x) * (1 - logistic(x))
class NeuralNetwork:
def __init__(self, layers, activation='tanh'):
"""
神經網絡算法構造函數
:param layers: 神經元層數
:param activation: 使用的函數(默認tanh函數)
:return:none
"""
if activation == 'logistic':
self.activation = logistic
self.activation_deriv = logistic_derivative
elif activation == 'tanh':
self.activation = tanh
self.activation_deriv = tan_deriv
# 權重列表
self.weights = []
# 初始化權重(隨機)
for i in range(1, len(layers) - 1):
self.weights.append((2 * np.random.random((layers[i - 1] + 1, layers[i] + 1)) - 1) * 0.25)
self.weights.append((2 * np.random.random((layers[i] + 1, layers[i + 1])) - 1) * 0.25)
def fit(self, X, y, learning_rate=0.2, epochs=10000):
"""
訓練神經網絡
:param X: 數據集(通常是二維)
:param y: 分類標記
:param learning_rate: 學習率(默認0.2)
:param epochs: 訓練次數(最大循環次數,默認10000)
:return: none
"""
# 確保數據集是二維的
X = np.atleast_2d(X)
temp = np.ones([X.shape[0], X.shape[1] + 1])
temp[:, 0: -1] = X
X = temp
y = np.array(y)
for k in range(epochs):
# 隨機抽取X的一行
i = np.random.randint(X.shape[0])
# 用隨機抽取的這一組數據對神經網絡更新
a = [X[i]]
# 正向更新
for l in range(len(self.weights)):
a.append(self.activation(np.dot(a[l], self.weights[l])))
error = y[i] - a[-1]
deltas = [error * self.activation_deriv(a[-1])]
# 反向更新
for l in range(len(a) - 2, 0, -1):
deltas.append(deltas[-1].dot(self.weights[l].T) * self.activation_deriv(a[l]))
deltas.reverse()
for i in range(len(self.weights)):
layer = np.atleast_2d(a[i])
delta = np.atleast_2d(deltas[i])
self.weights[i] += learning_rate * layer.T.dot(delta)
def predict(self, x):
x = np.array(x)
temp = np.ones(x.shape[0] + 1)
temp[0:-1] = x
a = temp
for l in range(0, len(self.weights)):
a = self.activation(np.dot(a, self.weights[l]))
return a