Recent Advances in Deep Learning (EE807, Fall 2018)

Deep learning is a new area of machine learning research, which have demonstrated states-of-the-art performance on many artificial intelligence tasks, e.g., computer vision, speech recognition and natural language processing. In this lecture, I will cover some of recent advances (made mostly in the last 5 years) in this area.

Announcement

• The maximum number of course registrations is around 40, and we cannot accept more now (do not send an email to Instructor or TA).

• The deadline for notifying whether you choose A or B to TA is Sep. 2 (see Lecture 0).

• Two deadlines for sending your project reports to TA are Oct. 21 and Dec 16, which are all we need for your credit.

• Office hours: Every Tuesday, 11am - 1pm, N1-914

• The final presentation for projects of Option A will be on Wednesday, Dec. 12 (10 minutes will be given for each student to talk).

• The claim for midterm project of Option B will be on Monday, Nov. 26, 1-3 PM at N1 917.

Schedule

• Lecture 0: Introduction to EE807

• Lecture 1: Introduction to neural networks

• Lecture 2: Stochastic gradient descent

• Lecture 3: Regularization

• Lecture 4: CNN architectures

• Lecture 5: Graphical models

• Lecture 6: RNN architectures

• Lecture 7: Deep reinforcement learning

• Lecture 8: Deep bayesian models

• Lecture 9: Generative adversarial networks

• Lecture 10: Auto-regressive/encoding and flow-based models

• Lecture 11: Transfer learning

• Lecture 12: Domain transfer and adaptation

• Lecture 13: Novelty detection for deep classifiers

• Lecture 14: Adversarial examples

• Lecture 15: Interpretable learning

• Lecture 16: Network compression

• Lecture 17: Meta learning

• Lecture 18: Advanced models for vision

• Lecture 19: Advanced models for language

• Lecture 20: Advanced models for speech

Other Deep Learning Lectures

• Introduction to Deep Learning (6.S191), Massachusetts Institute of Technology

• Introduction to Deep Learning (11-785), Carnegie Mellon University

• Deep Learning (CS1470), Brown University

• Theories of Deep Learning (STATS385), Stanford University

• Theoretical principles for deep learning (IFT 6085), University of Montreal

• Deep Learning (EE559), École Polytechnique Fédérale de Lausanne

• Deep Reinforcement Learning (CS294-112), UC Berkeley

• Natural Language Processing with Deep Learning (CS224n), Stanford University

• Deep Learning for Self-Driving Cars (6.S094), Massachusetts Institute of Technology

Contact

Instructor: Jinwoo Shin, jinwoos@kaist.ac.kr
TA: Insu Han, insu.han@kaist.ac.kr