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)

import numpy as np
from tensorflow.keras import layers, models
# 创建模型
model = models.Sequential()
model.add(layers.Dense(64, activation='relu', input_shape=(784,))) # 输入层到隐藏层1
model.add(layers.Dense(64, activation='relu')) # 隐藏层2
model.add(layers.Dense(10, activation='softmax')) # 输出层
# 编译模型
model.compile(optimizer=tf.train.AdamOptimizer(), loss='categorical_crossentropy')
# 加载数据集（这里使用MNIST手写字体数据集）
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# 对图像进行预处理
x_train, x_test = x_train / 255.0, x_test / 255.0
y_train = tf.keras.utils.to_categorical(y_train, num_classes=10)
y_test = tf.keras.utils.to_categorical(y_test, num_classes=10)
# 训练模型
model.fit(x_train, y_train, epochs=3, batch_size=32)
# 在测试集上评估模型性能
loss, accuracy = model.evaluate(x_test, y_test)
print('Test Loss: ', loss)
print('Test Accuracy: ', accuracy)