Seoul National University
M1522.001600 Topics in Big Data Analytics
Advanced Deep Learning
Fall 2017 - U Kang

News and Announcements

Course Information

Deep learning is a branch of machine learning based on a set of algorithms that attempt to model high level abstractions in data. Deep learning is a driving force of the recent advances in AI. In this course, we study advanced techniques of deep learning to analyze large amount of data. Topics include linear factor models, autoencoders, representation learning, structured probabilistic models for deep learning, monte carlo methods, partition function, approximate inference, and deep generative models.

Schedule

Date Topic Notice
Sep. 5 Introduction
7 Deep Feedforward Network (Chapter 6)
12 Deep Feedforward Network-2 (Chapter 6)
14 Deep Feedforward Network-3 (Chapter 6)
19 Linear Factor Model (Chapter 13)
21 Linear Factor Model-2 (Chapter 13)
26 Autoencoder (Chapter 14)
28 Autoencoder-2 (Chapter 14)
Oct. 3 Representation Learning (Chapter 15)
5 Representation Learning-2 (Chapter 15)
10 Representation Learning-3 (Chapter 15)
12 Structured Probabilistic Models for Deep Learning (Chapter 16)
17 Structured Probabilistic Models for Deep Learning-2 (Chapter 16)
19 Structured Probabilistic Models for Deep Learning-3 (Chapter 16)
24,26 Midterm
31 Monte Carlo Methods (Chapter 17)
Nov. 2 Monte Carlo Methods-2 (Chapter 17)
7 Confronting the Partition Function (Chapter 18)
9 Confronting the Partition Function-2 (Chapter 18)
14 Confronting the Partition Function-3 (Chapter 18)
16 Approximate Inference (Chapter 19)
21 Approximate Inference-2 (Chapter 19)
23 Approximate Inference-3 (Chapter 19)
28 Deep Generative Models (Chapter 20)
30 Deep Generative Models-2 (Chapter 20)
Dec. 5 Deep Generative Models-3 (Chapter 20)
7 Deep Generative Models-4 (Chapter 20)
12, 14 Final

Grading

Late policy - for all deliverables:

Textbook

The text book is
Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. (available in online)

Prerequisite

We expect you to have an undergraduate-level knowledge on the following topics:
Last modified Oct. 8, 2017, by U Kang