Detailed Syllabus and Lectures


Lecture 12: Deep Reinforcement Learning (slides)

what is reinforcement learning, markov decision processes, deep q-networks (DQNs), deep policy networks, model based reinforcement learning, alphago

Please study the following material in preparation for the class:

Required Reading:

Suggested Video Material:


Additional Resources:


Lecture 11: Deep Generative Models Part II (slides)

generative adversarial networks (GANs), conditional GANs, tips and tricks, applications of GANs

Please study the following material in preparation for the class:

Required Reading:

Suggested Video Material:


Additional Resources:


Lecture 10: Deep Generative Models Part I (slides1) (slides2)

applications of deep generative models, fully-observed models, transformation models, latent variable models, variational auto-encoders

Please study the following material in preparation for the class:

Required Reading:

Suggested Video Material:


Additional Resources:


Lecture 9: Representation Learning (slides1) (slides2)

supervised representation learning, unsupervised representation learning, sparse coding, autoencoders, restricted boltzman machines, deep belief networks

Please study the following material in preparation for the class:

Required Reading:

Suggested Video Material:


Additional Resources:


Lecture 8: Attention and Memory (slides1) (slides2)

attention mechanism for deep learning, attention for image captioning, memory networks, end-to-end memory networks, dynamic memory networks

Please study the following material in preparation for the class:

Required Reading:

Suggested Video Material:


Additional Resources: