What is the difference between Bidirectional RNN and RNN?

Ans: Bidirectional Recurrent Neural Networks (BRNN) means connecting two hidden layers of opposite directions to the same output, With this form of generative deep learning, the output layer can get information from past and future states at the same time. BRNNs were introduced to increase the amount of input information to the network. recurrent neural network also have restrictions as the future input information which cannot be reached from the current state. On the opposite side, BRNNs do not require their input data to be fixed. Furthermore, their future input information is accessible from the current state. BRNN are particularly useful when the context of the input is needed. Bidirectional recurrent neural networks is just putting two independent RNNs together. The input sequence is fed in normal time order for one network, and in reverse time order for another network. The outputs of the two networks are usually concatenated at each time step, though there are other options like summation.

This structure allows the network to have both backward and forward information about the sequence at every time step.

Neural network 61 (i2tutorials)

 

Neural network 62 (i2tutorials)