** The videos for course v2 using the new API(v4) of the course will be out soon!! **

We're back for round 2 of our ML workgroup and we will remain online for the duration of this course!!

Over the next few months we will work through the new version of the fast.ai course, "Practical Deep Learning For Coders v4, Part 1", this time using the latest version of the fast.ai api and the Fastbook.

Lesson 4: Under the Hood: Training a Digit Classifier, covering creating a dataset, broadcasting, calculating gradients, applying learning rates, loss functions and predictions!

Tentative Agenda:
18:30 - 18:45 - Social chat, introduce yourself, questions, etc
18:45 - Overview: Maria & Perusha
18:50 - 04_mnist_basics - Mark Oppenheim & Justin Evans
19:40 - Team Projects:
- Les will show us the ML Arduino project he has been working on (20min)
- Kalidass will show us his work on Deep Fakes (15 min)
- Show us your work or ask questions - open floor!

Links:
Notebook: https://github.com/fastai/fastbook/blob/master/clean/04_mnist_basics.ipynb

Course Details:

- Practical Deep Learning For Coders v4, Part 1 (using the new version of the API)
- The videos for Course v4 are not yet available however you can watch the Course-v3 videos. The videos will be out in the next week or so!!
- People are expected to have completed the material in their own time/pace before the event to be able to fully participate.
- We will space the online events 2-3 weeks apart to give people sufficient time to complete the assignments. It is likely that we will remain online until it is safe for everyone to re-emerge!
- There is a slack channel so if you have questions or need help please ask.

Reference slide deck with course material and resources:
https://docs.google.com/presentation/d/1uit7nLmloplxcPEmmjIC8nOaHWG67Eg2dqcYY6byOK0/edit?usp=sharing