单隐层神经网络 python_单隐藏层神经网络 实现逻辑门

import numpy as np

from numpy import exp

from sklearn import datasets

def sigma(z):

if z>=0:

return 1/(1+exp(-z))

else:

return exp(z)/(1+exp(z))

class Net:

def __init__(self, X, Y, num):

# num 是隐藏层神经元个数

self.num = num

self.B = np.zeros(num)

self.X = X

self.Y = Y

# self.wB = np.ones(num+1) #隐藏层和输出层间的连接权和阈值

np.random.seed(2)

self.wB = np.random.random(num+1) #隐藏层和输出层间的连接权和阈值

# self.WX = np.array([np.ones(X.shape[1]+1)*0.01 for i in range(num)]) #输入层和隐藏层间的连接权和阈值

self.WX = np.array([np.random.random(X.shape[1]+1)*0.01 for i in range(num)]) #输入层和隐藏层间的连接权和阈值

def cal_g(self, Xi, yi):

# print(Xi)

# 计算 输出层到隐藏层的 梯度变量, Xi 是一个输入

# 计算 隐藏层的值

for i in range(self.num):

self.B[i] = sigma(np.dot(np.append(Xi, np.array([-1])).T, self.WX[i]))

# 使用tanh当隐层激活函数，可比sigma更快收敛

# self.B[i] = np.tanh(np.dot(np.append(Xi, np.array([-1])).T, self.WX[i]))

# print(self.B[i])

# 计算 输出层的值

y = sigma(np.dot(np.append(self.B, np.array([-1])).T, self.wB))

g = (yi-y)*y*(1-y)

self.g = g

# print(f"g:{g}")

return g

def cal_e(self, Xi, yi):

# 计算 隐藏层到输入层的 梯度变量

# 先计算g

if not self.g:

g = self.cal_g(Xi, yi)

else: g = self.g

ret = []

for i in range(self.num):

b = self.B[i]

e = b*(1-b)*g*self.wB[i]

ret.append(e)

self.e = ret

def learn(self, pace=0.1, max_num=300):

r = self.Y.shape[0]

for j in range(max_num):

for i in range(r):

Xi = self.X[i]

yi = self.Y[i]

self.cal_g(Xi, yi)

self.cal_e(Xi, yi)

g = self.g

es = self.e

self.wB += pace*g*np.append(self.B, np.array([-1])) # 更新 隐层 和输出层之间的权值

for k in range(self.num):

self.WX[k] += pace*es[k]*np.append(Xi,np.array([-1]))

return True

def __call__(self, Xi):

for i in range(self.num):

# self.B[i] = np.tanh(np.dot(np.append(Xi, np.array([-1])).T, self.WX[i]))

self.B[i] = sigma(np.dot(np.append(Xi, np.array([-1])).T, self.WX[i]))

# 计算 输出层的值

y = sigma(np.dot(np.append(self.B, np.array([-1])).T, self.wB))

return 1 if y>=0.5 else 0

def test():

iris = datasets.load_iris()

def get_i(n):

while n:

yield n%2

n = n>>1

def get_t(n):

t = []

for i in get_i(n):

t.append(i)

while len(t)<4:

t.append(0)

return t

X = np.array([(1,1),(1,0),(0,0),(0,1)])

for Y in np.array([get_t(n) for n in range(15)]):

net = Net(X, Y, 2)

net.learn(max_num=30000)

a = np.array([net(np.array(x)) for x in ([1,1],[1,0],[0,0],[0,1])])

print(f"Y:{Y}\ta:{a}\t{all(a==Y)}")

test()