PowerBI Data Analyst - Create visualizations and dashboards from scratch
Launch Your Cybersecurity Career in 6 Months
Overview
Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This lecture examines recurrent neural networks for sequence problems, including vanishing gradients, LSTM variants, bidirectionality, and attention. It also discusses CTC loss, encoder-decoder LSTM tradeoffs, and a Google machine translation case study.
Syllabus
- Introduction
- Sequence Problems
- Review of RNNs
- Vanishing Gradient Issue
- LSTMs and Its Variants
- Bidirectionality and Attention from Google's Neural Machine Translation
- CTC Loss
- Pros and Cons of Encoder-Decoder LSTM Architectures
- WaveNet
Taught by
The Full Stack