Deep Learning / 15
RNNs, LSTMs & GRUs
Work through recurrent networks, backpropagation through time, LSTM gates, and GRUs.
This is a knowledge index. Published titles open their articles; the remaining entries outline planned coverage.
RNN
- 15.01
Recurrent Neural Networks
Planned guide: Recurrent Neural Networks. Focus on intuition, assumptions, and a worked example.
- 15.03
Recurrent Connections
Planned guide: Recurrent Connections. Focus on intuition, assumptions, and a worked example.
- 15.04
Backpropagation Through Time
Planned guide: Backpropagation Through Time. Focus on intuition, assumptions, and a worked example.
- 15.05
Vanishing Gradients in RNNs
Planned guide: Vanishing Gradients in RNNs. Focus on intuition, assumptions, and a worked example.
- 15.06
Exploding Gradients in RNNs
Planned guide: Exploding Gradients in RNNs. Focus on intuition, assumptions, and a worked example.
LSTM
- 15.07
LSTM
Planned guide: LSTM. Focus on intuition, assumptions, and a worked example.
- 15.08
Cell State
Planned guide: Cell State. Focus on intuition, assumptions, and a worked example.
- 15.09
Forget Gate
Planned guide: Forget Gate. Focus on intuition, assumptions, and a worked example.
- 15.10
Input Gate
Planned guide: Input Gate. Focus on intuition, assumptions, and a worked example.
- 15.11
Output Gate
Planned guide: Output Gate. Focus on intuition, assumptions, and a worked example.
GRU
- 15.12
GRU
Planned guide: GRU. Focus on intuition, assumptions, and a worked example.
- 15.13
Update Gate
Planned guide: Update Gate. Focus on intuition, assumptions, and a worked example.
- 15.14
Reset Gate
Planned guide: Reset Gate. Focus on intuition, assumptions, and a worked example.
- 15.15
LSTM vs GRU
Planned guide: LSTM vs GRU. Focus on intuition, assumptions, and a worked example.
Advanced
- 15.16
Bidirectional RNN
Planned guide: Bidirectional RNN. Focus on intuition, assumptions, and a worked example.
- 15.17
Stacked RNN
Planned guide: Stacked RNN. Focus on intuition, assumptions, and a worked example.
- 15.18
Encoder-Decoder RNN
Planned guide: Encoder-Decoder RNN. Focus on intuition, assumptions, and a worked example.


