机器学习、深度学习和神经网络之间的区别和联系
import numpy as np
# 定义Sigmoid函数
def sigmoid(x):
return 1 / (1 + np.exp(-x))
# 定义神经网络类
class NeuralNetwork:
def __init__(self, input_size, hidden_size, output_size):
# 初始化权重
self.W1 = np.random.randn(input_size, hidden_size)
self.W2 = np.random.randn(hidden_size, output_size)
def forward(self, X):
# 前向传播
self.z = np.dot(X, self.W1)
self.z2 = sigmoid(self.z)
self.z3 = np.dot(self.z2, self.W2)
output = sigmoid(self.z3)
return output
def backward(self, X, y, output, learning_rate):
# 反向传播
self.output_error = y - output
self.output_delta = self.output_error * sigmoid(output, derivative=True)
self.z2_error = self.output_delta.dot(self.W2.T)
self.z2_delta = self.z2_error * sigmoid(self.z2, derivative=True)
self.W1 += X.T.dot(self.z2_delta) * learning_rate
self.W2 += self.z2.T.dot(self.output_delta) * learning_rate
def train(self, X, y, learning_rate=1, epochs=10000):
for epoch in range(epochs):
output = self.forward(X)
self.backward(X, y, output, learning_rate)
def predict(self, X):
output = self.forward(X)
return output
# 创建一个神经网络实例
input_size = 2
hidden_size = 3
output_size = 1
nn = NeuralNetwork(input_size, hidden_size, output_size)
# 准备训练数据
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
y = np.array([[0], [1], [1], [0]])
# 训练神经网络
nn.train(X, y)
# 预测新的数据
new_data = np.array([0, 1])
prediction = nn.predict(new_data)
print("预测结果:", prediction)