LSTM Summary
- LSTMs extend RNNs with gated cells to remember long-term context, addressing RNN gradient issues.
- Core update: \( C_t = f_t \odot C_{t-1} + i_t \odot \tilde{C}_t \), output \( h_t = o_t \odot \tanh(C_t) \).
- Implementation is straightforward in libraries like Keras/PyTorch with few lines of code.
- Applications span science and engineering: forecasting dynamical systems, analyzing DNA/proteins, etc.
- For more details, see Goodfellow et al. (2016) Deep Learning, chapter 14