Recurrent Neural Network
How RNNs, LSTMs, and GRUs process sequential data, the vanishing gradient problem, and where recurrent models still apply.
Sequence-Modeling
State Space Model
How structured state space models like Mamba and S4 achieve linear-time sequence modeling as an alternative to transformers.
Temporal Convolutional Network
How causal dilated convolutions provide an efficient alternative to RNNs for sequence modeling with parallelizable training.