反向传播误差：神经网络预测同类

Question

我正在用Numpy从头开始编写神经网络代码。但是，即使在我的网络训练了很多个时期之后，每个类的预测都是随机的，不管输入的是什么，预测都是一样的。你知道吗

我根据Andrew Ng的CursRML课程检查了我的概念。towardsdatascience.com网站的职位。我想我犯了一些概念上的错误，我想不出来。你知道吗

这是我的密码：

import numpy as np

def sigmoid(x):
    return 1 / (1 + np.exp(-x))

def dsigmoid(y):
    return y * (1 - y)

class NeuralNetwork:
    def __init__(self, shape):
        self.n_layers = len(shape)
        self.shape = shape

        self.weight = []
        self.bias = []

        i = 0
        while i < self.n_layers - 1:
            self.weight.append(np.random.normal(loc=0.0, scale=0.5, 
                                                size=(self.shape[i + 1], self.shape[i])))
            self.bias.append(np.random.normal(loc=0.0, scale=0.3,
                                                size=(self.shape[i + 1], 1)))
            i += 1

    def predict(self, X):
        z = self.weight[0] @ X + self.bias[0]
        a = sigmoid(z)
        i = 1
        while i < self.n_layers - 1:
            z = self.weight[i] @ a + self.bias[i]
            a = sigmoid(z)
            i += 1

        return a

    def predictVerbose(self, X):
        layers = [X]
        z = self.weight[0] @ X + self.bias[0]
        a = sigmoid(z)
        layers.append(a)
        i = 1
        while i < self.n_layers - 1:
            z = self.weight[i] @ a + self.bias[i]
            a = sigmoid(z)
            layers.append(a)
            i += 1

        return layers

    def gradOne(self, X, y):
        layers = self.predictVerbose(X)
        h = layers[-1]

        delta_b = [(h - y) * dsigmoid(h)]
        delta_w = [delta_b[0] @ layers[-2].T]

        i = 1
        while i < self.n_layers - 1:
            buff = delta_b[-1]
            delta_b.append((self.weight[-i].T @ buff) * dsigmoid(layers[-(i + 1)]))
            delta_w.append(delta_b[-1] @ layers[-(i + 2)].T)
            i += 1


        return delta_b[::-1], delta_w[::-1]

    def grad(self, data, l_reg=0):
        #data: x1, x2, x3, ..., xm, y=(0, 1, 2,...)
        m = len(data)
        delta_b = []
        delta_w = []
        i = 0
        while i < self.n_layers - 1:
            delta_b.append(np.zeros((self.shape[i + 1], 1)))
            delta_w.append(np.zeros((self.shape[i + 1], self.shape[i])))
            i += 1


        for row in data:
            X = np.array(row[:-1])[np.newaxis].T
            y = np.zeros((self.shape[-1], 1))
            # print(row)
            y[row[-1], 0] = 1
            buff1, buff2 = self.gradOne(X, y)
            i = 0
            while i < len(delta_b):
                delta_b[i] += buff1[i] / m
                delta_w[i] += buff2[i] / m
                i += 1

        return delta_b, delta_w


    def train(self, data, batch_size, epoch, alpha, l_reg=0):
        m = len(data)
        for i in range(epoch):
            j = 0
            while j < m:
                delta_b, delta_w = self.grad(data[i: (i + batch_size + 1)])
                i = 0
                while i < len(self.weight):
                    self.weight[i] -= alpha * delta_w[i]
                    self.bias[i] -= alpha * delta_b[i]
                    i += 1
                j += batch_size        



if __name__ == "__main__":
    x = NeuralNetwork([2, 2, 2])
    # for y in x.gradOne(np.array([[1], [2], [3]]), np.array([[0], [1]])):
    #     print(y.shape)

    data = [
        [1, 1, 0],
        [0, 0, 0],
        [1, 0, 1],
        [0, 1, 1]
    ]

    x.train(data, 4, 1000, 0.1)
    print(x.predict(np.array([[1], [0]])))
    print(x.predict(np.array([[1], [1]])))

请指出我错在哪里。你知道吗

Answer 1

不幸的是，我没有足够的声誉来评论你的文章，但这里有一个链接到一个numpy唯一的神经网络，我已经做了（测试从sklearn和mnist的blob数据）。你知道吗

https://github.com/jaymody/backpropagation/blob/master/old/NeuralNetwork.py