神经网络：BP算法&Python实现

2020_10_30

神经网络：BP算法

误差逆传播算法（Error BackPropagation，简称BP），是多层神经网络中最成功的神经网络学习算法。

Python

import numpy as np
import matplotlib.pyplot as plt

x = np.array([2, 5], dtype=float)
y_true = np.array([3, 6, 4], dtype=float)

# sigmond
def sigmoid(x):
    s = 1 / (1 + np.exp(-x))
    return s

def sigmoid_derivative(x):
    s = 1 / (1 + np.exp(-x))
    ds = s * (1 - s)
    return ds

def BP(x, y, num):
    epochs = 20000
    learning_rate = 0.3 

    I_num = x.shape[0]
    H_num = num
    O_num = y.shape[0]
    
    V = np.random.rand(I_num, H_num) - 0.5
    dV = np.random.rand(I_num, H_num)

    W = np.random.rand(H_num, O_num) - 0.5
    dW = np.random.rand(H_num, O_num)

    mse_record = np.ones((1, epochs))

    for step in range(epochs):
        # Forward
        H_in = np.dot(x, V) # 1