神经网络代码

神经网络的代码通常使用深度学习框架来实现，比如TensorFlow、PyTorch、Keras等。以下是一个使用TensorFlow实现的简单的全连接神经网络的代码示例：

import tensorflow as tf

# 定义神经网络结构
n_inputs = 28*28  # MNIST图像像素点数
n_hidden1 = 300
n_hidden2 = 100
n_outputs = 10  # 10个数字分类

# 定义输入输出占位符
X = tf.placeholder(tf.float32, shape=(None, n_inputs), name="X")
y = tf.placeholder(tf.int64, shape=(None), name="y")

# 定义神经网络层
with tf.name_scope("dnn"):
    hidden1 = tf.layers.dense(X, n_hidden1, name="hidden1",
                              activation=tf.nn.relu)
    hidden2 = tf.layers.dense(hidden1, n_hidden2, name="hidden2",
                              activation=tf.nn.relu)
    logits = tf.layers.dense(hidden2, n_outputs, name="outputs")

# 定义损失函数和优化器
with tf.name_scope("loss"):
    xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)
    loss = tf.reduce_mean(xentropy, name="loss")
with tf.name_scope("train"):
    optimizer = tf.train.GradientDescentOptimizer(learning_rate)
    training_op = optimizer.minimize(loss)

# 定义评估指标
with tf.name_scope("eval"):
    correct = tf.nn.in_top_k(logits, y, 1)
    accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))

# 训练模型
n_epochs = 40
batch_size = 50
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for epoch in range(n_epochs):
        for iteration in range(mnist.train.num_examples // batch_size):
            X_batch, y_batch = mnist.train.next_batch(batch_size)
            sess.run(training_op, feed_dict={X: X_batch, y: y_batch})
        acc_train = accuracy.eval(feed_dict={X: X_batch, y: y_batch})
        acc_test = accuracy.eval(feed_dict={X: mnist.test.images, y: mnist.test.labels})
        print(epoch, "Train accuracy:", acc_train, "Test accuracy:", acc_test)

以上代码实现了一个有两个隐藏层的全连接神经网络，用于对MNIST手写数字进行分类。代码中使用了TensorFlow提供的高层API，如`tf.layers.dense`实现了全连接层的定义，`tf.train.GradientDescentOptimizer`实现了梯度下降优化器的定义等。