Lesson 4 - NLP, Tabular, and Collaborative Filtering
This topic is for official updates and information regarding Lesson 4. Only admins are able to reply to this thread, so please subscribe to topic notifications to ensure you don’t miss anything. You should also follow the general course update thread.
Note that this is a forum wiki thread, so you all can edit this post to add/change/organize info to help make it better! To edit, click on the little edit icon at the bottom of this post. Here’s a pic of what to look for:
Note that you need the newly released version 1.0.24 of fastai for this lesson. Be sure to git pull and to conda update to have the most up-to-date materials.
Lesson resources
- Notebooks:
- Excel spreadsheets:
- Links to different parts in video by @melonkernel
- Lesson notes by @PoonamV
- Detailed lesson notes by @hiromi
- Brief lesson notes from @boy1729
- Lesson 4 in-class discussion
- Lesson 4 advanced discussion
Other resources
- QCon.ai keynote on Analyzing & Preventing Unconscious Bias in Machine Learning
- PyBay keynote with case studies of what can go wrong, and steps toward solutions
- Workshop on Word Embeddings, Bias in ML, Why You Don’t Like Math, & Why AI Needs You
- AI Ethics Resources (includes links to experts to follow)
- What HBR Gets Wrong About Algorithms and Bias
- When Data Science Destabilizes Democracy and Facilitates Genocide
- Vim and Ctags for fast function definition lookup
- Pinterest case study mentioned around 38:00
- References in video
Bias & Ethics resources (will be covered in more detail in a future lesson, but came up during in-class discussion)