Past Meetup

Deep Learning Study Group Workshop (week 7 of 7)

This Meetup is past

27 people went

Location image of event venue

Details

This study group workshop series is following the fast.ai deep learning MOOC week-by-week. We are now in the final week, so please be aware that there's a lot of catching up to do if you are only just starting out on the course!

What is fast.ai?

According to their website, fast.ai helps you to: “Learn how to build state of the art models without needing graduate-level math—but also without dumbing anything down… You will start with step one—learning how to get a GPU server online suitable for deep learning—and go all the way through to creating state of the art, highly practical, models for computer vision, natural language processing, and recommendation systems.” (http://course.fast.ai/)

Please note that we have no official connection with fast.ai whatsoever; we are just using their materials as a basis for our own workshops.

And what is this workshop series about?

This week we shall continue to follow the 2018 version of the fast.ai course, Practical Deep Learning for Coders, Part 1, week by week. This course was originally delivered late last year at the University of San Francisco by Jeremy Howard (Kaggle's #1 competitor 2 years running). The course lectures and other materials have been kindly made available free online by fast.ai in MOOC form.

How are these workshops going to work?

Each session we will use that week’s fast.ai lectures and course materials as a basis for discussion and learning. We will briefly introduce each of the key topics from that week’s lecture, and then invite everyone to contribute their insights and questions about it, work through important aspects of the notebooks etc.

What would my role be as a participant in the workshop?

We hope that everyone will be able to contribute something while they are learning. Note that we are not formally “teaching” deep learning in these workshops, but rather providing a participation-oriented environment for everyone to learn together.

What kind of time commitment is involved?

Prior to each workshop, we would request that you at least watch the lecture for that week (typically these are around 2 hours long; shorter if you play them back at 1.25x speed!). If you are able to spend a few more hours each week working on the supplementary course materials, that would be ideal.

If you don’t think that you are going to be able to commit enough time to the course, please don’t sign up — leave spots open for those who do have the time to study and come every week.

What tools does the course use?

The fast.ai course is based around Python 3.6, so familiarity with numpy and pandas is required. For the deep learning component, fast.ai supplies its own package (fastai) which is built on top of PyTorch, a python package for tensor computation and deep learning. OK,

I’m in. What do I need to do before the final workshop?

1. Watch all seven videos at http://course.fast.ai/

3. Take a look at the supplementary materials at http://forums.fast.ai/t/wiki-lesson-7/9405 and/or these excellent student notes: https://medium.com/@hiromi_suenaga/deep-learning-2-part-1-lesson-7-1b9503aff0c

4. Install the PyTorch and fastai packages.

5. (Ideally!) Prepare any questions you may have and/or insights that you would like to share with the group. Of course, it’s OK to jump ahead and watch some of the other videos in the series!

Here are some more resources for week 7:

fast.ai course home page: http://course.fast.ai/index.html

The final lecture: http://course.fast.ai/lessons/lesson7.html

Week 7 course wiki: http://forums.fast.ai/t/wiki-lesson-7/9405

You might also find these excellent notes by one of the students useful: https://medium.com/@hiromi_suenaga/deep-learning-2-part-1-lesson-7-1b9503aff0c

The course forum is here: http://forums.fast.ai/

The fast.ai GitHub containing all the course notebooks is here: https://github.com/fastai/fastai/tree/master/courses/dl1

The fastai Python package is here: https://github.com/fastai/fastai/tree/master/fastai