使用隐藏层解决非线性问题

本文主要是介绍使用隐藏层解决非线性问题，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

使用隐藏层解决非线性问题：

                    输入层：    隐藏层：   输出层： 

                           

import tensorflow as tf
import numpy as nplearning_rate = 0.0001
n_input = 2
n_label = 1
n_hidden = 2x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_label])weights = {'h1': tf.Variable(tf.truncated_normal([ n_input, n_hidden], stddev =0.1)),'h2': tf.Variable(tf.truncated_normal([n_hidden, n_label], stddev =0.1))
}
biases = {'h1': tf.Variable(tf.zeros([n_hidden])),'h2': tf.Variable(tf.zeros([n_label]))
}layer_1 = tf.nn.relu(tf.add(tf.matmul(x, weights['h1']), biases['h1']))
y_pred = tf.nn.tanh(tf.add(tf.matmul(layer_1,weights['h2']), biases['h2']))loss = tf.reduce_mean((y_pred - y)**2)
train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss)X = [[0,0],[0,1],[1,0],[1,1]]
Y = [[0],[1],[1],[0]]
X = np.array(X).astype('float32')
Y = np.array(Y).astype('int16')# 迭代训练模型
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
for i in range(1000):sess.run(train_step, feed_dict = {x:X, y:Y})# 计算预测值print(sess.run(y_pred, feed_dict={x:X}))# 查看隐藏层的输出print(sess.run(layer_1, feed_dict = {x:X}))

结果：

[[ 9.9999961e-05]
 [-1.2277756e-03]
 [-1.2540328e-02]
 [-1.3875227e-02]]
[[0.         0.        ]
 [0.01804843 0.        ]
 [0.17182861 0.        ]
 [0.18997703 0.        ]]
[[ 0.0002    ]
 [-0.00111128]
 [-0.01240848]
 [-0.01373422]]

......

这篇关于使用隐藏层解决非线性问题的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！

---