1
我正在尝试使用numpy实现一个简单的RNN（基于this article），并且我正在训练它做二进制加法，它一次只增加两个8位无符号整数（从结尾开始），在需要的时候学习如何“添加一个”。但是，它似乎并没有学习。对于训练，我选择两个随机数，以a和b中的一位作为输入向前传播8个步骤，并在每个时间步中存储输出和隐藏层值，并反向传播8个步骤，我计算隐藏层错误（output_error.dot(weights_hidden_to_output.T)) * sigmoid_to_derivative(hidden) + future_hidden_error.dot(weights_hidden_to_hidden.T)）以及通过矩阵将父层与子层的错误相乘来对每个权重矩阵进行更新。这是正确的方法吗？为什么不是我的RNN学习？
这是我的代码，如果它会使它更清晰。我注意到由于某种原因，每次训练时权重开始突然增加，并且它们引起S形函数的溢出，导致训练失败。任何想法可能导致这种情况？
import numpy as np
np.random.seed(0)
def sigmoid(x):
return np.atleast_2d(1/(1+np.exp(-x)))
#return np.atleast_2d(np.max(x, 0.01))
def sig_deriv(x):
return x*(1-x)
def add_bias(x):
return np.hstack([np.ones((len(x), 1)), x])
def dec_to_bin(dec):
return np.array(map(int, list(format(dec, '#010b'))[2:]))
def bin_to_dec(b):
out = 0
for bit in b:
out = (out << 1) | bit
return out
batch_size = 8
learning_rate = .1
input_size = 2
hidden_size = 16
output_size = 1
weights_xh = 2 * np.random.random((input_size+1, hidden_size)) - 1
weights_hh = 2 * np.random.random((hidden_size+1, hidden_size)) - 1
weights_hy = 2 * np.random.random((hidden_size+1, output_size)) - 1
xh_update = np.zeros_like(weights_xh)
hh_update = np.zeros_like(weights_hh)
hy_update = np.zeros_like(weights_hy)
for i in xrange(10000):
a = np.random.randint(0, 2**batch_size/2)
b = np.random.randint(0, 2**batch_size/2)
sum_ = a+b
X = add_bias(np.hstack([np.atleast_2d(dec_to_bin(a)).T, np.atleast_2d(dec_to_bin(b)).T]))
y = np.atleast_2d(dec_to_bin(sum_)).T
error = 0
output_errors = []
outputs = []
hiddens = [add_bias(np.zeros((1, hidden_size)))]
#forward propagation through time
for j in xrange(batch_size):
hidden = sigmoid(X[-j-1].dot(weights_xh) + hiddens[-1].dot(weights_hh))
hidden = add_bias(hidden)
hiddens.append(hidden)
output = sigmoid(hidden.dot(weights_hy))
outputs.append(output[0][0])
output_error = (y[-j-1] - output)
error += np.abs(output_error[0])
output_errors.append((output_error * sig_deriv(output)))
future_hidden_error = np.zeros((1,hidden_size))
#backward ppropagation through time
for j in xrange(batch_size):
output_error = output_errors[-j-1]
hidden = hiddens[-j-1]
prev_hidden = hiddens[-j-2]
hidden_error = (output_error.dot(weights_hy.T) * sig_deriv(hidden)) + future_hidden_error.dot(weights_hh.T)
hidden_error = np.delete(hidden_error, 0, 1) #delete bias error
xh_update += np.atleast_2d(X[j]).T.dot(hidden_error)
hh_update += prev_hidden.T.dot(hidden_error)
hy_update += hidden.T.dot(output_error)
future_hidden_error = hidden_error
weights_xh += (xh_update * learning_rate)/batch_size
weights_hh += (hh_update * learning_rate)/batch_size
weights_hy += (hy_update * learning_rate)/batch_size
xh_update *= 0
hh_update *= 0
hy_update *= 0
if i%1000==0:
guess = map(int, map(round, outputs[::-1]))
print "Iteration {}".format(i)
print "Error: {}".format(error)
print "Problem: {} + {} = {}".format(a, b, sum_)
print "a: {}".format(list(dec_to_bin(a)))
print "+ b: {}".format(list(dec_to_bin(b)))
print "Solution: {}".format(map(int, y))
print "Guess: {} ({})".format(guess, bin_to_dec(guess))
print