我有一个神经网络 (NN)，它在应用于单个数据集时效果很好。但是，如果我想在一组数据上运行 NN，然后创建一个新的 NN 实例以在不同的数据集（甚至是同一组数据）上运行，那么新实例将产生完全不正确的预测.
例如，在 XOR 模式上进行训练：
test=[[0,0],[0,1],[1,0],[1,1]]
data = [[[0,0], [0]],[[0,1], [0]],[[1,0], [0]],[[1,1], [1]]]
n = NN(2, 3, 1) # Create a neural network with 2 input, 3 hidden and 1 output nodes
n.train(data,500,0.5,0) # Train it for 500 iterations with learning rate 0.5 and momentum 0
prediction = np.zeros((len(test)))
for row in range(len(test)):
prediction[row] = n.runNetwork(test[row])[0]
print prediction
#
# Now do the same thing again but with a new instance and new version of the data.
#
test2=[[0,0],[0,1],[1,0],[1,1]]
data2 = [[[0,0], [0]],[[0,1], [0]],[[1,0], [0]],[[1,1], [1]]]
p = NN(2, 3, 1)
p.train(data2,500,0.5,0)
prediction2 = np.zeros((len(test2)))
for row in range(len(test2)):
prediction2[row] = p.runNetwork(test2[row])[0]
print prediction2
将输出：
[-0.01 -0. -0.06 0.97]
[ 0. 0. 1. 1.]
请注意，第一个预测非常好，而第二个完全错误，我看不出这个类有什么问题：
import math
import random
import itertools
import numpy as np
random.seed(0)
def rand(a, b):
return (b-a)*random.random() + a
def sigmoid(x):
return math.tanh(x)
def dsigmoid(y):
return 1.0 - y**2
class NN:
def __init__(self, ni, nh, no):
# number of input, hidden, and output nodes
self.ni = ni + 1 # +1 for bias node
self.nh = nh + 1
self.no = no
# activations for nodes
self.ai = [1.0]*self.ni
self.ah = [1.0]*self.nh
self.ao = [1.0]*self.no
# create weights (rows=number of features, columns=number of processing nodes)
self.wi = np.zeros((self.ni, self.nh))
self.wo = np.zeros((self.nh, self.no))
# set them to random vaules
for i in range(self.ni):
for j in range(self.nh):
self.wi[i][j] = rand(-5, 5)
for j in range(self.nh):
for k in range(self.no):
self.wo[j][k] = rand(-5, 5)
# last change in weights for momentum
self.ci = np.zeros((self.ni, self.nh))
self.co = np.zeros((self.nh, self.no))
def runNetwork(self, inputs):
if len(inputs) != self.ni-1:
raise ValueError('wrong number of inputs')
# input activations
for i in range(self.ni-1):
#self.ai[i] = sigmoid(inputs[i])
self.ai[i] = inputs[i]
# hidden activations
for j in range(self.nh-1):
sum = 0.0
for i in range(self.ni):
sum = sum + self.ai[i] * self.wi[i][j]
self.ah[j] = sigmoid(sum)
# output activations
for k in range(self.no):
sum = 0.0
for j in range(self.nh):
sum = sum + self.ah[j] * self.wo[j][k]
self.ao[k] = sigmoid(sum)
ao_simplified = [round(a,2) for a in self.ao[:]]
return ao_simplified
def backPropagate(self, targets, N, M):
if len(targets) != self.no:
raise ValueError('wrong number of target values')
# calculate error terms for output
output_deltas = [0.0] * self.no
for k in range(self.no):
error = targets[k]-self.ao[k]
output_deltas[k] = dsigmoid(self.ao[k]) * error
# calculate error terms for hidden
hidden_deltas = [0.0] * self.nh
for j in range(self.nh):
error = 0.0
for k in range(self.no):
error = error + output_deltas[k]*self.wo[j][k]
hidden_deltas[j] = dsigmoid(self.ah[j]) * error
# update output weights
for j in range(self.nh):
for k in range(self.no):
change = output_deltas[k]*self.ah[j]
self.wo[j][k] = self.wo[j][k] + N*change + M*self.co[j][k]
self.co[j][k] = change
#print N*change, M*self.co[j][k]
# update input weights
for i in range(self.ni):
for j in range(self.nh):
change = hidden_deltas[j]*self.ai[i]
self.wi[i][j] = self.wi[i][j] + N*change + M*self.ci[i][j]
self.ci[i][j] = change
# calculate error
error = 0.0
for k in range(len(targets)):
error = error + 0.5*(targets[k]-self.ao[k])**2
return error
def train(self, patterns, iterations=1000, N=0.5, M=0.1):
# N: learning rate
# M: momentum factor
for i in range(iterations):
error = 0.0
for p in patterns:
inputs = p[0]
targets = p[1]
self.runNetwork(inputs)
error = error + self.backPropagate(targets, N, M)
if i % 100 == 0: # Prints error every 100 iterations
print('error %-.5f' % error)
任何帮助将不胜感激！