Intermediate · every module free · 6 challenges
Forward pass, backward pass and a working network in NumPy before you are allowed to import a framework.
Initialization, normalization, dropout, weight decay and the vanishing gradient -- everything between a network that exists and one that converges.
Learning rate schedules, warmup, batch size effects, gradient clipping and mixed precision.
Error analysis, data-centric iteration, baselines and knowing which experiment to run next.
Convolutions, the architectures that mattered, detection and segmentation, and vision transformers.
RNNs, LSTMs, encoder-decoders and the attention mechanism that replaced them.