Python实现的递归神经网络简单示例
作者:罗兵 时间:2022-03-26 04:19:48
本文实例讲述了Python实现的递归神经网络。分享给大家供大家参考,具体如下:
# Recurrent Neural Networks
import copy, numpy as np
np.random.seed(0)
# compute sigmoid nonlinearity
def sigmoid(x):
output = 1/(1+np.exp(-x))
return output
# convert output of sigmoid function to its derivative
def sigmoid_output_to_derivative(output):
return output*(1-output)
# training dataset generation
int2binary = {}
binary_dim = 8
largest_number = pow(2,binary_dim)
binary = np.unpackbits(
np.array([range(largest_number)],dtype=np.uint8).T,axis=1)
for i in range(largest_number):
int2binary[i] = binary[i]
# input variables
alpha = 0.1
input_dim = 2
hidden_dim = 16
output_dim = 1
# initialize neural network weights
synapse_0 = 2*np.random.random((input_dim,hidden_dim)) - 1
synapse_1 = 2*np.random.random((hidden_dim,output_dim)) - 1
synapse_h = 2*np.random.random((hidden_dim,hidden_dim)) - 1
synapse_0_update = np.zeros_like(synapse_0)
synapse_1_update = np.zeros_like(synapse_1)
synapse_h_update = np.zeros_like(synapse_h)
# training logic
for j in range(10000):
# generate a simple addition problem (a + b = c)
a_int = np.random.randint(largest_number/2) # int version
a = int2binary[a_int] # binary encoding
b_int = np.random.randint(largest_number/2) # int version
b = int2binary[b_int] # binary encoding
# true answer
c_int = a_int + b_int
c = int2binary[c_int]
# where we'll store our best guess (binary encoded)
d = np.zeros_like(c)
overallError = 0
layer_2_deltas = list()
layer_1_values = list()
layer_1_values.append(np.zeros(hidden_dim))
# moving along the positions in the binary encoding
for position in range(binary_dim):
# generate input and output
X = np.array([[a[binary_dim - position - 1],b[binary_dim - position - 1]]])
y = np.array([[c[binary_dim - position - 1]]]).T
# hidden layer (input ~+ prev_hidden)
layer_1 = sigmoid(np.dot(X,synapse_0) + np.dot(layer_1_values[-1],synapse_h))
# output layer (new binary representation)
layer_2 = sigmoid(np.dot(layer_1,synapse_1))
# did we miss?... if so, by how much?
layer_2_error = y - layer_2
layer_2_deltas.append((layer_2_error)*sigmoid_output_to_derivative(layer_2))
overallError += np.abs(layer_2_error[0])
# decode estimate so we can print(it out)
d[binary_dim - position - 1] = np.round(layer_2[0][0])
# store hidden layer so we can use it in the next timestep
layer_1_values.append(copy.deepcopy(layer_1))
future_layer_1_delta = np.zeros(hidden_dim)
for position in range(binary_dim):
X = np.array([[a[position],b[position]]])
layer_1 = layer_1_values[-position-1]
prev_layer_1 = layer_1_values[-position-2]
# error at output layer
layer_2_delta = layer_2_deltas[-position-1]
# error at hidden layer
layer_1_delta = (future_layer_1_delta.dot(synapse_h.T) + layer_2_delta.dot(synapse_1.T)) * sigmoid_output_to_derivative(layer_1)
# let's update all our weights so we can try again
synapse_1_update += np.atleast_2d(layer_1).T.dot(layer_2_delta)
synapse_h_update += np.atleast_2d(prev_layer_1).T.dot(layer_1_delta)
synapse_0_update += X.T.dot(layer_1_delta)
future_layer_1_delta = layer_1_delta
synapse_0 += synapse_0_update * alpha
synapse_1 += synapse_1_update * alpha
synapse_h += synapse_h_update * alpha
synapse_0_update *= 0
synapse_1_update *= 0
synapse_h_update *= 0
# print(out progress)
if j % 1000 == 0:
print("Error:" + str(overallError))
print("Pred:" + str(d))
print("True:" + str(c))
out = 0
for index,x in enumerate(reversed(d)):
out += x*pow(2,index)
print(str(a_int) + " + " + str(b_int) + " = " + str(out))
print("------------")
运行输出:
Error:[ 3.45638663]
Pred:[0 0 0 0 0 0 0 1]
True:[0 1 0 0 0 1 0 1]
9 + 60 = 1
------------
Error:[ 3.63389116]
Pred:[1 1 1 1 1 1 1 1]
True:[0 0 1 1 1 1 1 1]
28 + 35 = 255
------------
Error:[ 3.91366595]
Pred:[0 1 0 0 1 0 0 0]
True:[1 0 1 0 0 0 0 0]
116 + 44 = 72
------------
Error:[ 3.72191702]
Pred:[1 1 0 1 1 1 1 1]
True:[0 1 0 0 1 1 0 1]
4 + 73 = 223
------------
Error:[ 3.5852713]
Pred:[0 0 0 0 1 0 0 0]
True:[0 1 0 1 0 0 1 0]
71 + 11 = 8
------------
Error:[ 2.53352328]
Pred:[1 0 1 0 0 0 1 0]
True:[1 1 0 0 0 0 1 0]
81 + 113 = 162
------------
Error:[ 0.57691441]
Pred:[0 1 0 1 0 0 0 1]
True:[0 1 0 1 0 0 0 1]
81 + 0 = 81
------------
Error:[ 1.42589952]
Pred:[1 0 0 0 0 0 0 1]
True:[1 0 0 0 0 0 0 1]
4 + 125 = 129
------------
Error:[ 0.47477457]
Pred:[0 0 1 1 1 0 0 0]
True:[0 0 1 1 1 0 0 0]
39 + 17 = 56
------------
Error:[ 0.21595037]
Pred:[0 0 0 0 1 1 1 0]
True:[0 0 0 0 1 1 1 0]
11 + 3 = 14
------------
英文原文:https://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/
希望本文所述对大家Python程序设计有所帮助。
来源:http://www.cnblogs.com/hhh5460/p/5782539.html
标签:Python,递归
![](/images/zang.png)
![](/images/jiucuo.png)
猜你喜欢
python修改包导入时搜索路径的方法
2023-05-12 07:40:23
拖拽翻页(ThrowPage)详解 cool
2009-12-02 09:54:00
![](https://img.aspxhome.com/file/UploadPic/200912/2/01-46s.jpg)
RDFa介绍——构建更友好的web页面
2009-09-19 17:01:00
事件检测
2009-04-11 18:03:00
yui3的AOP(面向切面编程)和OOP(面向对象编程)
2009-09-24 14:47:00
![](https://img.aspxhome.com/file/UploadPic/20099/24/p_large_a3t9_42d000010d432d0e-12s.jpg)
47个惊人的CSS3动画演示
2010-02-07 12:32:00
![](https://img.aspxhome.com/file/UploadPic/20102/7/csstricks-clock-97s.jpg)
谈谈我的“分离”观
2010-08-31 14:47:00
css基础教程布局篇之一
2008-07-31 17:21:00
![](https://img.aspxhome.com/file/UploadPic/20087/31/200873117275859s.jpg)
python中的内置函数max()和min()及mas()函数的高级用法
2023-01-21 18:45:43
![](https://img.aspxhome.com/file/2023/6/76096_0s.jpg)
ASP用户登录模块的设计
2008-11-21 16:55:00
Python代码调试的几种方法总结
2022-06-14 18:21:27
![](https://img.aspxhome.com/file/2023/5/71475_0s.jpg)
学会Python数据可视化必须尝试这7个库
2022-03-26 20:37:25
![](https://img.aspxhome.com/file/2023/5/70195_0s.png)
SQL根据时间范围条件查询数据
2009-01-18 13:32:00
Python科学计算包numpy用法实例详解
2021-11-12 15:07:20
回调函数的意义以及python实现实例
2021-07-17 11:42:07
Phar反序列化超详细介绍
2023-06-05 07:06:02
![](https://img.aspxhome.com/file/2023/8/55368_0s.png)
ASP 下载时重命名已上传文件的新下载文件名的实现代码
2012-11-30 20:33:45
python列表的常用操作方法小结
2023-06-21 16:14:34
教你怎么使用sql游标实例分享
2012-07-11 16:14:57
简单了解什么是神经网络
2023-10-11 22:26:34
![](https://img.aspxhome.com/file/2023/8/89318_0s.png)