一文彻底搞懂RNN、BPTT（递归神经网络）
RNN：递归神经网络（RNN）是时间递归神经网络（recurrent neural network）和结构递归神经网络（recursive neural
network）的总称。时间递归神经网络的神经元间连接构成矩阵，而结构递归神经网络结构更加复杂。
【基本描述】
1、递归神经网络RNN主要用来处理序列有关数据whatsapp网页版，比如时间序列、文本序列等。序列是被排成一列的对象，RNN处理序列对象之所以存在优势，是因为RNN神经元中充分考虑了序列输入中前段时间一定的权重。
2、RNN网络结构：和传统神经网络一样，RNN网络结构分为输入层、隐藏层和输出层
RNN网络特别之处在于如下：SYNAPSE_h会连接当前t时刻的隐藏层神经元whatsapp网页版，同时也连接着t-1时刻的神经元结构，所以RNN神经网络中的参数主要有SYNAPSE_O对应的U矩阵，SYNAPSE_h对应的W矩阵和SYNAPSE_1对应的V矩阵，如下图U是3*3矩阵，W是4*4矩阵，V是4*2矩阵。
3、公式推导_前向传播
前向传播相对简单，其主要涉及的公式见下：
4、公式推导_反向传播
【实例】
例：用RNN来实现一个八位的二进制数加法运算。
import copy, numpy as np np.random.seed(0) # compute sigmoid nonlinearity def
sigmoid(x): output = 1 / (1 + np.exp(-x)) return output # convert output of
sigmoid function to its derivative def sigmoid_output_to_derivative(output):
return output * (1 - output) # training dataset generation int2binary = {}
binary_dim = 8 largest_number = pow(2, binary_dim) binary = np.unpackbits(
np.array(
range(largest_number)
, dtype=np.uint8).T, axis=1) for i in
range(largest_number): int2binary
= binary
# input variables alpha = 0.1
input_dim = 2 hidden_dim = 16 output_dim = 1 # initialize neural network
weights synapse_0 = 2 * np.random.random((input_dim, hidden_dim)) - 1 synapse_1
= 2 * np.random.random((hidden_dim, output_dim)) - 1 synapse_h = 2 *
np.random.random((hidden_dim, hidden_dim)) - 1 synapse_0_update =
np.zeros_like(synapse_0) synapse_1_update = np.zeros_like(synapse_1)
synapse_h_update = np.zeros_like(synapse_h) # training logic for j in
range(10000): # generate a simple addition problem (a + b = c) a_int =
np.random.randint(largest_number / 2) # int version a = int2binary
a_int
binary encoding b_int = np.random.randint(largest_number / 2) # int version b =
int2binary
b_int
# binary encoding # true answer c_int = a_int + b_int c =
int2binary
c_int
# where we'll store our best guess (binary encoded) d =
np.zeros_like(c) overallError = 0 layer_2_deltas = list() layer_1_values =
list() layer_1_values.append(np.zeros(hidden_dim)) # moving along the positions
in the binary encoding for position in range(binary_dim): # generate input and
output X = np.array(
binary_dim - position - 1
, b
binary_dim - position -
) y = np.array(
binary_dim - position - 1
).T # hidden layer (input ~+
prev_hidden) layer_1 = sigmoid(np.dot(X, synapse_0) +
np.dot(layer_1_values
-1
, synapse_h)) # output layer (new binary
representation) layer_2 = sigmoid(np.dot(layer_1, synapse_1)) # did we miss?...
if so, by how much? layer_2_error = y - layer_2
layer_2_deltas.append((layer_2_error) * sigmoid_output_to_derivative(layer_2))
overallError += np.abs(layer_2_error
) # decode estimate so we can print it
out d
binary_dim - position - 1
= np.round(layer_2
) # store hidden layer
so we can use it in the next timestep
layer_1_values.append(copy.deepcopy(layer_1)) future_layer_1_delta =
np.zeros(hidden_dim) for position in range(binary_dim): X =
np.array(
position
, b
position
) layer_1 = layer_1_values
-position - 1
prev_layer_1 = layer_1_values
-position - 2
# error at output layer
layer_2_delta = layer_2_deltas
-position - 1
# error at hidden layer
layer_1_delta = (future_layer_1_delta.dot(synapse_h.T) + layer_2_delta.dot(
synapse_1.T)) * sigmoid_output_to_derivative(layer_1) # let's update all our
weights so we can try again synapse_1_update +=
np.atleast_2d(layer_1).T.dot(layer_2_delta) synapse_h_update +=
np.atleast_2d(prev_layer_1).T.dot(layer_1_delta) synapse_0_update +=
X.T.dot(layer_1_delta) future_layer_1_delta = layer_1_delta synapse_0 +=
synapse_0_update * alpha synapse_1 += synapse_1_update * alpha synapse_h +=
synapse_h_update * alpha synapse_0_update *= 0 synapse_1_update *= 0
synapse_h_update *= 0 # print out progress if (j % 1000 == 0): print("Error:" +
str(overallError)) print("Pred:" + str(d)) print("True:" + str(c)) out = 0 for
index, x in enumerate(reversed(d)): out += x * pow(2, index) print(str(a_int) +
" + " + str(b_int) + " = " + str(out)) print("------------")
以上源码经过几次得到就能得到很好的效果，详细的执行逻辑可以跟踪代码进行查看！
【总结】
时间递归神经网络可以描述动态时间行为，但是简单递归神经网络无法处理随着递归whatsapp登录，梯度爆炸或者梯度消失的问题，并且难以捕捉长期时间关联；有效的处理方法是忘掉错误的信息，记住正确的信息。LSTM能够比较好的解决这个问题。