[MXDL-10-08] Recurrent Neural Networks (RNN) [8/8] - Multi-layer and Bi-directional RNN

So far, we have implemented many-to-one and many-to-many models. In other forms, we can implement single-layer and multi-layer models, and unidirectional and bidirectional models. We can also implement models that combine all of these.

Then we can implement recurrent neural networks in many different forms. For example, we can implement a two-layered, unidirectional many-to-one model, or a two-layered, bidirectional many-to-many model.

In this video, we'll use these combinations to implement several types of recurrent neural network models.

#RecurrentNeuralNetwork #LSTM #MultilayerRNN #BidirectionalRNN