## Recent Advances in Deep Learning (AI602, Fall 2019)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. ## AnnouncementThe maximum number of course registrations is around 40, and we cannot accept more now (do not send an email to Instructor or TA). Office hours: Every Tuesday, 11am - 1pm, N1-914
## ScheduleLecture 0: Introduction to AI602 Lecture 1: Introduction to neural networks Lecture 2: Optimization and regularization Lecture 3: CNN architectures Lecture 4: RNN architectures Lecture 5: Transfer and multi-task learning Lecture 6: Adversarial examples Lecture 7: GNN architectures Lecture 8: Deep generative models I: GAN Lecture 9: Deep generative models II: VAE and others Lecture 10: Deep reinforcement learning Lecture 11: Novelty and uncertainty estimation Lecture 12: Unsupervised and semi-supervised learning Lecture 13: Domain transfer and adaptation Lecture 14: Meta learning Lecture 15: Interpretable learning Lecture 16: Network compression Lecture 17: Deep bayesian models Lecture 18: Active learning and experimental design
## Other Deep Learning LecturesIntroduction 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
## ContactInstructor: Jinwoo Shin (jinwoos@kaist.ac.kr) |