Deep Learning Course (NYU, Spring 2020) - Week 6 – Practicum: RNN and LSTM architectures

Course website: http://bit.ly/DLSP20-web Playlist: http://bit.ly/pDL-YouTube Speaker: Alfredo Canziani Week 6: http://bit.ly/DLSP20-06 0:00:00 – Week 6 – Practicum PRACTICUM: http://bit.ly/DLSP20-06-3 We discussed architecture of Vanilla RNN and LSTM models and compared the performance between the two. LSTM inherits advantages of RNN, while improving RNN’s weaknesses by including a ‘memory cell’ to store information in memory for long periods of time. LSTM models significantly outperforms RNN models. 0:00:21 – Overview and 4 types of RNN 0:14:15 – RNN Training and related issues 0:30:38 – Long Short-Term Memory and Notebook Examples