tensorflow学习——简单RNN实现

import numpy as npX = [1,2]state = [0.0, 0.0]w_cell_state = np.asarray([[0.1, 0.2],[0.3, 0.4]])w_cell_input = np.asarray([0.5,0.6])b_cell = np.asarray([0.1, -0.1])#定义用于输出的全连接层参数w_output = np.asarray([[1.0], [2.0]])b_output = 0.1#按照时间顺序执行循环神经网络的前向传播过程for i in range(len(X)):    #计算循环体中的全连接蹭神经网络    before_activation = np.dot(state, w_cell_state) + X[i] * w_cell_input + b_cell    state = np.tanh(before_activation)    #根据当前时刻状态计算最终输出    final_output = np.dot(state, w_output) + b_output    #输出每个时刻的信息    print "before activation: ",before_activation    print "state: ",state    print"output: ",final_output

输出如下：