TensorFlow-递归神经网络 (TensorFlow - Recurrent Neural Networks)
Recurrent neural networks is a type of deep learning-oriented algorithm, which follows a sequential approach. In neural networks, we always assume that each input and output is independent of all other layers. These type of neural networks are called recurrent because they perform mathematical computations in sequential manner.
递归神经网络是一种面向深度学习的算法,它遵循顺序方法。 在神经网络中,我们始终假设每个输入和输出都独立于所有其他层。 这些类型的神经网络称为递归,因为它们以顺序的方式执行数学计算。
Consider the following steps to train a recurrent neural network −
考虑以下步骤来训练递归神经网络-
Step 1 − Input a specific example from dataset.
步骤1-从数据集中输入特定示例。
Step 2 − Network will take an example and compute some calculations using randomly initialized variables.
步骤2-网络将以一个示例为例,并使用随机初始化的变量来计算一些计算。
Step 3 − A predicted result is then computed.
步骤3-然后计算预测结果。
Step 4 − The comparison of actual result generated with the expected value will produce an error.
步骤4-将生成的实际结果与期望值进行比较会产生错误。
Step 5 − To trace the error, it is propagated through same path where the variables are also adjusted.
步骤5-要跟踪错误,它会通过相同的路径传播,在该路径中也会对变量进行调整。
Step 6 − The steps from 1 t