Syllabus

Tuesday 9:10-12:10 (Online)

Date Description Course Material Note
2020/03/03
slido		 [Course Logistics]
[Introduction] (1.1) (1.2) (1.3) 		[Registration Form]
A0 A0: Playing PyTorch [A0 slides] Due on 03/03 23:59
2020/03/10
slido		 [Neural Network Basics] (2.1) (2.2) (2.3) (2.4)
[Backpropagation] (2.5)
Suggested Readings:
  1. [Linear Algebra]
  2. [Linear Algebra Slides]
  3. [Linear Algebra Quick Review]
TA - [Optimization] (2.6)
2020/03/17
slido		 [Word Representation] (3.1)
[Recurrent Neural Network] (3.2) (3.3) (3.4) 		Suggested Readings:
  1. [Learning Representations]
  2. [Vector Space Models of Semantics]
  3. [RNNLM]
  4. [Extensions of RNNLM]
  5. [RNN for Language Understanding]
  6. [Sequence-to-Sequence Learning]
  7. [Neural Conversational Model]
 TA - [Pactical Tips] (3.5)
A1 A1: Summarization [A1 pages] (video) Due on 04/07 23:59
2020/03/24
slido		 [Attention Mechanism] (4.1) (4.2)
[HW1 Brief Tutorial] (video)
 Suggested Readings:
  1. [Summarization with Attention]
  2. [Neural Machine Translation]
2020/03/31 slido [Word Embeddings] (5.1) (5.2) (5.3) (5.4) (5.5) (5.6) (5.7)
[Contextual Embeddings: ELMo] (5.8) (5.9) 		Suggested readings:
  1. [Word2Vec]
  2. [GloVe: Global Vectors]
  3. [Contextual Word Representations Introduction]
  4. [ELMo: Embeddings from Language Models]
2020/04/07 slido [Transformer] (6.1) (6.2) (6.3) (6.4)
[BERT] (6.5) 		Suggested readings:
  1. [Attention is all you need]
  2. [BERT: Pre-training of Bidirectional Transformers]
  3. [GPT: Improving Understanding by Unsupervised Learning]
 TA - [More Embeddings] (6.6)
A2 A2: BERT for QA [A2 pages] (video)
2020/04/14 slido [More BERT] (7.1) (7.2) (7.3) (7.4) TA - [More Transformers] (7.5)
2020/04/21 Midterm Break
2020/04/28 slido [Deep Reinforcement Learning] (8.1) (8.2) (8.3)
[Q-Learning] (8.4) (8.5)
 Suggested Readings:
  1. [Reinforcement Learning Intro]
  2. [Stephane Ross' thesis]
  3. [Playing Atari with DRL]
  4. [Double Q-learning]
  5. [Dueling Network Architectures]
2020/05/05 slido [Policy & Actor-Critic] (9.1) (9.2)

Suggested Readings:
  1. [Asynchronous Methods for DRL]
  2. [Deterministic Policy Gradient]
  3. [Continuous Control with DRL]
A3 A3: Deep Reinforcement Learning [A3 pages] (video)
2020/05/12 slido [Natural Language Generation] (10.1) (10.2) (10.3) (10.4) Suggested Readings:
  1. [How NOT to Evaluate Your Dialog System]
  2. [How Controllable Attributes Affect Human Judgements]
  3. [Sequence-Level Training with RNN]
  4. [Reinforced Summarization]
 TA - [RL for Dialogues] (10.5)
2020/05/19 Guest Lecture (Prof. Hung-Yi Lee)
[Generative Adversarial Network]
(Overview) (Basic Theory) (Tips for Improvement)
Project Final Project:
1) Transfer Learning
2) Propose Your Own 		[Project Description] (video)
[Project Rules / Grading] (video) 		Video Due on 6/23 23:59
Report Due on 6/28 23:59
2020/05/26 slido [Beyond Supervised Learning] (11.1) (11.2) (11.3)
Suggested Readings:
  1. [Tutorial on VAE]
  2. [MT-DNN]
2020/06/02 slido [Towards Conversational AI] (12.1) (12.2) (12.3)
2020/06/09 Break
2020/06/16 [Robustness and Scalability] (13.1) (13.2)
[Career Sharing] (video) 		[Project Rules / Grading] (video)
2020/06/23 Final Presentation

What's New?

Feb 13 - Website launch.