这篇文章主要介绍了python实现的递归神经网络,是一篇摘录自github代码片段的文章,涉及python递归与数学运算相关操作技巧,需要的朋友可以参考下
本文实例讲述了python实现的递归神经网络。分享给大家供大家参考，具体如下：
# recurrent neural networks 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[i] = binary[i] # 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([[a[binary_dim - position - 1],b[binary_dim - position - 1]]]) y = np.array([[c[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[0]) # decode estimate so we can print(it out) d[binary_dim - position - 1] = np.round(layer_2[0][0]) # 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([[a[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("------------")
运行输出：
error:[ 3.45638663] pred:[0 0 0 0 0 0 0 1] true:[0 1 0 0 0 1 0 1] 9 + 60 = 1 ------------ error:[ 3.63389116] pred:[1 1 1 1 1 1 1 1] true:[0 0 1 1 1 1 1 1] 28 + 35 = 255 ------------ error:[ 3.91366595] pred:[0 1 0 0 1 0 0 0] true:[1 0 1 0 0 0 0 0] 116 + 44 = 72 ------------ error:[ 3.72191702] pred:[1 1 0 1 1 1 1 1] true:[0 1 0 0 1 1 0 1] 4 + 73 = 223 ------------ error:[ 3.5852713] pred:[0 0 0 0 1 0 0 0] true:[0 1 0 1 0 0 1 0] 71 + 11 = 8 ------------ error:[ 2.53352328] pred:[1 0 1 0 0 0 1 0] true:[1 1 0 0 0 0 1 0] 81 + 113 = 162 ------------ error:[ 0.57691441] pred:[0 1 0 1 0 0 0 1] true:[0 1 0 1 0 0 0 1] 81 + 0 = 81 ------------ error:[ 1.42589952] pred:[1 0 0 0 0 0 0 1] true:[1 0 0 0 0 0 0 1] 4 + 125 = 129 ------------ error:[ 0.47477457] pred:[0 0 1 1 1 0 0 0] true:[0 0 1 1 1 0 0 0] 39 + 17 = 56 ------------ error:[ 0.21595037] pred:[0 0 0 0 1 1 1 0] true:[0 0 0 0 1 1 1 0] 11 + 3 = 14 ------------
以上就是解析python实现递归神经网络的问题的详细内容。