Deep learning is a vast area with many different facets. We briefly list a few important topics that we never really looked at in class.
Reinforcement learning.
Auto-encoders.
Generative adversarial networks.
Representation learning.
RNNs and LSTMs.
Transformers.
Adversarial examples.
Hardness of training.
Uncertainty quantification.
The neural tangent kernel.
Non-linear training and Wasserstein gradient flows.
Neural networks, PDEs and scientific computing.