Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers the continuation of recurrent neural networks with multiple layers and bidirectionality, focusing on LSTM and GRU variants. It discusses the challenges of learning long-range dependencies, the use of gates in GRUs, and the advantages of LSTMs and GRUs over traditional RNNs. The instructor explains the concepts through practical examples and addresses issues like vanishing gradients and optimal architectures for different tasks.