除激活功能外,我有两个相同的感知器算法。一个使用单步函数1 if u >= 0 else -1
,另一个使用tanh函数np.tanh(u)
。
我预计tanh的表现会超过这一步,但实际上它的表现相当可观。我在这里做错了什么,或者有没有理由说它在问题集上表现不佳?
import numpy as np
import matplotlib.pyplot as plt
# generate 20 two-dimensional training data
# data must be linearly separable
# C1: u = (0,0) / E = [1 0; 0 1]; C2: u = (4,0), E = [1 0; 0 1] where u, E represent centre & covariance matrix of the
# Gaussian distribution respectively
def step(u):
return 1 if u >= 0 else -1
def sigmoid(u):
return np.tanh(u)
c1mean = [0, 0]
c2mean = [4, 0]
c1cov = [[1, 0], [0, 1]]
c2cov = [[1, 0], [0, 1]]
x = np.ones((40, 3))
w = np.zeros(3) # [0, 0, 0]
w2 = np.zeros(3) # second set of weights to see how another classifier compares
t = [] # target array
# +1 for the first 20 then -1
for i in range(0, 40):
if i < 20:
t.append(1)
else:
t.append(-1)
x1, y1 = np.random.multivariate_normal(c1mean, c1cov, 20).T
x2, y2 = np.random.multivariate_normal(c2mean, c2cov, 20).T
# concatenate x1 & x2 within the first dimension of x and the same for y1 & y2 in the second dimension
for i in range(len(x)):
if i >= 20:
x[i, 0] = x2[(i-20)]
x[i, 1] = y2[(i-20)]
else:
x[i, 0] = x1[i]
x[i, 1] = y1[i]
errors = []
errors2 = []
lr = 0.0001
n = 10
for i in range(n):
count = 0
for row in x:
dot = np.dot(w, row)
response = step(dot)
errors.append(t[count] - response)
w += lr * (row * (t[count] - response))
count += 1
for i in range(n):
count = 0
for row in x:
dot = np.dot(w2, row)
response = sigmoid(dot)
errors2.append(t[count] - response)
w2 += lr * (row * (t[count] - response))
count += 1
print(errors[-1], errors2[-1])
# distribution
plt.figure(1)
plt.plot((-(w[2]/w[0]), 0), (0, -(w[2]/w[1])))
plt.plot(x1, y1, 'x')
plt.plot(x2, y2, 'ro')
plt.axis('equal')
plt.title('Heaviside')
# training error
plt.figure(2)
plt.ylabel('error')
plt.xlabel('iterations')
plt.plot(errors)
plt.title('Heaviside Error')
plt.figure(3)
plt.plot((-(w2[2]/w2[0]), 0), (0, -(w2[2]/w2[1])))
plt.plot(x1, y1, 'x')
plt.plot(x2, y2, 'ro')
plt.axis('equal')
plt.title('Sigmoidal')
plt.figure(4)
plt.ylabel('error')
plt.xlabel('iterations')
plt.plot(errors2)
plt.title('Sigmoidal Error')
plt.show()
编辑:即使从错误图中我已经显示tanh函数显示出一些收敛,所以假设只是增加迭代或降低学习速率将允许它减少其错误是合理的。但是我想我真的在问,考虑到阶梯函数的显着更好的性能,对于什么问题集是否可以使用感知器使用tanh?