單層感知器實踐

import numpy as np
import matplotlib.pyplot as plt

#輸入數據
X = np.array([[3,3],
              [4,3],
              [1,1],
              [0,2]])

# 添加偏置項
X = np.concatenate((np.ones((4,1)),X),axis=1)
print(X)

# 標籤
Y = np.array([[1],
              [1],
              [-1],
              [-1]])
# 權值初始化，3行1列，取值範圍-1到1
W = (np.random.random([3,1])-0.5) *2

print(W)

# 學習率設置
lr = 0.11
# 神經網絡輸出
O = 0

def update():
    global X,Y,W,lr
    O = np.sign(np.dot(X,W))
    W_C = lr * (X.T.dot(Y-O))/int(X.shape[0])
    W = W + W_C

for i in range(100):
    update() # 更新當前權值
    print(W) # 打印當前權值
    print(i) # 打印迭代次數
    O = np.sign(np.dot(X,W))
    if (O == Y).all():
        print('Finished')
        print('epoch',i)
        break

#正樣本
x1 = [3,4]
y1 = [3,3]

#負樣本
x2 = [1,0]
y2 = [1,2]

#計算分界線的斜率以及截距
# w0 + w1x1 + w2x2 = 0
# x1 看作x x2看作y
# y = -w0/w2 - w1/w2(x)
k = -W[1] / W[2]
d = -W[0] / W[2]

xdata = (0,5)

plt.figure()
plt.plot(xdata,xdata * k +d,'r')
plt.scatter(x1,y1,c='b')
plt.scatter(x2,y2,c='y')
plt.show()