Course Logistics
Applied Deep Learning
March 3rd, 2020 http://adl.miulab.tw
Course Logistics
◉
Instructor: 陳縕儂 Yun-Nung (Vivian) Chen◉
Time: Tuesday 234, 9:10-12:20◉
Location: 資102 / Online◉
Website: http://adl.miulab.tw◉
NTU COOL: https://cool.ntu.edu.tw/courses/918/◉
Email: [email protected]○
To ensure timely response, email title should contain “[ADL2020]”○
Do NOT send to our personal emails2
Always check the up-to-date information from the course website
NTU COOL for Fighting Coronavirus
◉
NTU COOL○
Lecture videos■
Comments anytime○
Assignment submission (還可以寫 code 呢!)◉
Slido QA○
#ADL200303◉
TA Team○
Forum discussion (preferred)○
Email QA○
TA recitation○
TA hours (physical and online)3
Course Goal
◉
The students are expected to understand1.
how deep learning works2.
how to frame tasks into learning problems3.
how to use toolkits to implement designed models, and4.
when and why specific deep learning techniques work for specific problems4
Pre-requisites
◉
Course○
Required: college-level calculus, linear algebra○
Preferred: probability, statistics◉
Programming○
proficiency in Python; all assignments will be in Python○
GitHub; all assignments will be handed in via GitHub○
Kaggle; all assignments will be submitted to Kaggle5
(tutorialfrom Stanford) (tutorial) (website)
Please consider your available resources for taking this course
GitHub Student Pack
◉
The student plan provides unlimited private repositories○
make your assignments private before the due date○
make them public afterwards6
Grading Policy
◉
3 Individual Assignment: 20% x 3 = 60%○
GitHub code w/ README■
The score is based on coding and the report■
Bonus points for outstanding performance■
Late policy: 25% off per day late afterwards◉
Final Group Project: 30%○
GitHub code, Project document■
Bonus points for the outstanding work○
Final presentation (format TBA)◉
Participation: 10%○
Forum/slido discussion involvement○
Write-up for the special events7
Understanding the difference between “collaboration” and “academic infraction”
Individual Assignments
8
A1. Text Summarization A2. Transformer / BERT A3. Language Generation
Final Group Project (2~5 persons)
◉
Choose your preferred project topic○
Presentation■
Poster or online presentation■
Outstanding projects will be selected for awards/prizes○
Project Report & Code■
Wrap-up project report■
GitHub code submission w/ README 9The project details will be announced later
How to Get the Registration Code?
◉
Limit: ~100 students per course◉
Requirements○
Available GPU Resources○
Programming skills○
Finish HW0○
Fill in the Google Form10
Tentative Schedule
11
Week Topic Assignment
1 2020/03/03 Course Logistics & Introduction A0 – Pytorch Tutorial 2 2020/03/10 NN Basics & Backpropagation
3 2020/03/17 Word Representations + RNN A1 – Summarization 4 2020/03/24 Attention & Gating Mechanisms
5 2020/03/31 Word Embeddings + ELMo
6 2020/04/07 Transformer + BERT A2 – BERT
7 2020/04/14 More BERT
8 2020/04/21 RL Intro + Basic Q-Learning
9 2020/04/28 Policy Gradient + Actor-Critic A3 – NLG 10 2020/05/05 RL-Based NLG
11 2020/05/12 Adversarial Training + Generative Models Final Project 12 2020/05/19 Beyond Supervised Learning
13 2020/05/26 Advanced Learning Techniques 14 2020/06/02 Special Topic + Career Discussion 15 2020/06/09 Buffer Week
16 2020/06/16 Final Project Presentation
Teaching Assistant Team
12
Rules
13
Asking online questions is encouraged!!
Any comment or feedback is preferred!!
(speed, style, etc)
Attending TA hours!! (details TBA)
Any questions ?
You can find the course information at
◉ http://adl.miulab.tw
◉ YouTube: Vivian NTU MiuLab
Thanks!
14
