body { padding-top: 60px; } .dropdown { display: none; position: absolute; text-decoration: none; box-shadow: 3px 3px 5px #505050; } .nav-item:hover .dropdown{ display:block; } .dropdown-item a { text-decoration: none; color:black; }

School of Computing

Deep Learning via Fast.AI

NUS SoC, 2017/2018, Semester II
CS 6101 - Exploration of Computer Science Research

Last updated: February 12, 2018 - Synced new titles for PDLC 2018, and guest roster.
January 24, 2018 - Updated syllabus and added video links.
January 11, 2018 - Updated, especially links.
December 7, 2017 - First port of the page.

This is a section of the CS 6101 Exploration of Computer Science Research at NUS, School of Computing, for the Spring (Sem II) semester of 2017/2018 Academic Year. CS 6101 is a 4 modular credit pass/fail module for new incoming graduate programme students to obtain background in an area with an instructor's support. It is designed as a "lab rotation" to familiarize students with the methods and ways of research in a particular research area. The lab rotation is hosted by the Web IR / NLP Group (WING) at NUS, led by Min-Yen Kan.

This section will be running through the self-paced, publicly available deep learning material on the fast.ai website. Our section will be conducted as a group seminar, with class participants nominating themselves and presenting the materials and leading the discussion.

This "course" is offered twice, for Session I (Weeks 3-7)and Session II (Weeks 8-13), although it is clear that the course is logically a single course that builds on the first half. Session I mostly will cover the Practical Deep Learning for Coders short course, and Session II will cover the (no longer really) Cutting Edge Deep Learning for Coders (currently deep learning is evolving rather quickly so materials are outdated on a weekly basis). Nevertheless, the material should be introductory and should be understandable given some prior study.

A discussion group will be on Slack . Students and guests, please login when you are free. If you have a @comp.nus.edu.sg, @u.nus.edu, @nus.edu.sg, @a-star.edu.sg, @dsi.a-star.edu.sg or @i2r.a-star.edu.sg email address you can create your Slack account for the group discussion without needing an invite.

Meeting Venue and Time

10:00-11:00, Fridays for both Sessions I (Weeks 3-7) and Session II (Weeks 8-13).

Updated Venue is Meeting Room 6 (MR6; AS6 #05-10) . External guests are also encouraged to participate remotely via Slack and watch the cast via Google Hangouts / YouTube. Note: The sessions will be recorded to YouTube Live, to help others (e.g., those absent) review the sessions and for posterity.

For directions to NUS School of Computing (SoC) and COM1: please read the directions here, to park in CP15 or take the shuttle bus to SoC. and use the floorplan and map to find MR6.

People

Welcome. If you are an external visitor and would like to join us, please email Kan Min-Yen to be added to the class role. Guests from industry, schools and other far-reaching places in SG welcome, pending space and time logistic limitations. SoC and non-SoC NUS guests are also welcomed, but please note that only first year Ph.D. students are allowed to gain credit for the course. There will be no official certificates of completion given to students completing this course.

External guests will be listed here in due course once the course has started. Please refer to our Slack after you have been invited for the most up-to-date information.

NUS (Postgraduate): Session I (Weeks 3-7): Jiang Kan, Rrubaa Panchendrarajan

Other NUS: Rajan Dhingra, Joel Lee, Yong Ler Lee, Gabriella Ong, Sravani Satpathy

WING: Yuchen He, Shenhao Jiang, Animesh Prasad

Guests: Anirudh Venu, Edwin Wan

Syllabus

Links below refer to the either the original version 1 of the course (webpage with embedded video), or version 2 (direct YouTube link). Fast.AI recommends that you watch from their page so that you can benefit from any updated video and forum links. Please do oblige them, these links are provided just for your convenience.

 

DateDescriptionDeadlines
Preflight (on your own)
PDLC 0, 1
Getting Started (v1), and Recognizing Cats and Dogs (v1, v2)
Week 3: 2 Feb 2018
PDLC 2
Improving your Image Classifier (v1, v2) [ Session Recording ]
Presenters: Min
Week 4: 9 Feb 2018
PDLC 3
Understanding Convolutions (v1, v2) [ Session Recording ]
Presenters:
Slack Moderators: Radhika Nikam, Yong Ler
Week 5: (Rescheduled and relocated due to CNY)
19 16 Feb 2018
MR1 (COM1 #03-19)
PDLC 4
Structured, Time Series, & Language Models (v1, v2) [ Session Recording ]
Presenters: Jiang Kan, Rrubaa Panchendrarajan
Slack Moderators: Yuchen He
Week 6: 23 Feb 2018
PDLC 5
Collaborative Filtering; Inside the Training Loop (v1, v2) [ Session Recording ]
Presenters: Yong Ler
Slack Moderators: Rrubaa Panchendrarajan
Preliminary project titles and team members due on Slack's #projects
Week Recess: 2 Mar 2018
PDLC 6
Interpreting Embeddings; RNNS from Scratch (v1, v2) [ Session Recording ]
Presenters: Radhika Nikam
Slack Moderators: Edwin Wan
Week 7: 9 Mar 2018
PDLC 7
ResNets from Scratch (v1, v2) [ Session Recording ]
Presenters: Yuchen He
Slack Moderators: Jiang Kan
Preliminary abstracts due to #projects
Week 8: 16 Mar 2018
CEDLC 8
Artistic Style [ Session Recording ]
Presenters: Shenhao Jiang
Slack Moderators: Anirudh Venu
Week 9: 23 Mar 2018
CEDLC 9
Generative Models [ Session Recording ]
Presenters: Gabriella Ong
Slack Moderators: Shenhao Jiang, Rajan Dhingra
Week 10: (Rescheduled and relocated due to Good Friday) 2 Apr 30 Mar 2018
MR1 (COM1 #03-19)
CEDLC 10
Multi-Modal and GANs [ Session Recording ]
Presenters: Anirudh Venu
Slack Moderators: Joel Lee, Sravani Satpathy
Week 11: 6 Apr 2018
CEDLC 11
Memory Networks [ Session Recording ]
Presenters: Rajan Dhingra, Joel Lee, Sravani Satpathy
Slack Moderators: Gabriella Ong
Week 12: 13 Apr 2018
CEDLC 12
Attentional Models [ Session Recording ]
Presenters: Edwin Wan
Slack Moderators:
Week 13: 20 Apr 2018
CEDLC 13
Neural Translation [ Session Recording ]
Presenters:
Slack Moderators:
Participation on evening of 18 Apr: 12th STePS
Week Reading: 27 Apr 2018
CEDLC 14
Time Series and Experimentation [ Session Recording ]
Presenters:
Slack Moderators:

Student Projects

Student projects are required for all students (inclusive of external guests to the course, and all students in the course with and without conflicting lecture timings). All student projects can be done in any sized team, and will be featured in the 12th SoC Term Project Showcase (STePS).

Other Links