Foundations
Recurrent Networks
Memory over time, and why it eventually broke.
You can jump straight in, but this star assumes Training & Optimization. Not recommended as a first stop.
Four layers of depth
Each layer ends with a quiz. Finish layer 4 and you own this concept.
- L1IntuitionWhy sequences (text, audio, time series) need networks with memory, and what an RNN intuitively does.5m
40 XP - L2MechanicsThe recurrence equation, why vanilla RNNs struggle with long sequences, and how LSTMs/GRUs fix it with gates.8m
70 XP - L3CodeImplementing a vanilla RNN cell from scratch and an LSTM-based sequence model in PyTorch.12m
110 XP - L4FoundationsBackpropagation through time, why vanishing gradients are provably worse for recurrence, and the LSTM's gating math.15m
180 XP
33 stars in the atlas.