CENG 793 Advanced Deep Learning (Spring 2019)

Instructor:	Gokberk Cinbis
Syllabus:	Please read the syllabus for course details.

Image taken from https://research.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html

Weekly Schedule

Week	Lectures
	Overview lectures: Introduction, course logistics [slides]
	Overview lecture: Hallmarks of deep learning [slides] Review: loss functions [slides] Review: optimization [slides] Review: back-propagation [slides]
	Overview lecture: Review: neural-network basics [slides] Review: conv-net basics [slides] Review: GAN and VAE basics
	Generative Adversarial Networks (GANs) and improvements:
	Improving GANs: Overview lecture: Overview of RNNs
	No class.
	Meta-learning, Memory, NTMs:
	Deep Probabilistic Modeling and Inference:
	Project progress presentations.
	Variational Inference, optimization:
	Advances on autoregressive flows, continuous-domain formulations:
	Reinforcement Learning Resources Francois-Lavet et al. - An Introduction to Deep Reinforcement Learning Richard S. Sutton and Andrew G. Barto - Reinforcement Learning: An Introduction
	Attention for Vision and Language:
	Attention for Vision and Language:
	No class
	Final presentations, Thursday 9am-1pm, BMB3

Paper presentation guidelines

Please prepare your presentation as a lecture that puts the paper into context, rather than presenting a dry summary of the contents of a single paper.
Therefore, please cover important related work (if not already throughly covered in the class) in your presentation, in order to (i) make the presentation accessible for everyone, and, (ii) properly discuss the strengths and weaknesses of the paper compared to related work.
Each presenter is required to upload a near-complete draft of the slides (as a pdf) 2 days before the presentation date to ODTUclass and send me a simple notification email.
Each presenter is required to re-upload the final version of the slides on the presentation date. Slides will be published on the course webpage.
Please also see week 1 slides for some additional information.
The following will be used for grading: rubric.

Project

Projects can be done individually or as a group (working in groups is encouraged). The goal of the projects is to conduct research at the quality of publications appearing in premier venues. Due dates are announced on ODTUclass.

Milestones dates:

Project groups and proposals Each project group is required to submit a one-page project proposal.
Progress report Each group will prepare a progress report and presentation.
Final report Each group will prepare a final report and presentation.
Please use the ODTUClass submission page. Emailed submissions (unless Moodle is down) and late submissions will not be accepted.
All reports must be prepared using the IEEE double-column conference template. Using LaTeX (or LyX) is recommended. Final report should be around 8 page long.