Abstract
This lecture overviews Recurrent Neural Networks and Long Short-Term Memory (LSTM) networks that have many applications in signal and video analysis. It covers the following topics in detail: Neural Networks for Sequence Analysis. Recurrent Neural Networks and their relation to State space filters. RNN forward propagation. Activation functions. Loss functions and RNN training through Back-Propagation. Long Short-Term Memory. LSTM forward propagation. Gated Recurrent Unit. GRU forward propagation. It also overviews the following applications: Image Captioning, Object tracking, and Image denoising.
RNN architecture.
LSTM in video summarization.
Recurrent Neural Networks. LSTMs v4.6.3 - Summary