To fix fastai on Google Colab, add a cell with the following, then restart the runtime.

!pip install -U fastbook torchtext==0.8.1

• MIT 6.S191 Introduction to Deep Learning

• Videos

  • Fundamentals 009 (Linear Regression with Learner) walkthrough

  • Lab 3 walkthrough

• Our book: Deep Learning for Coders

  • Source notebooks, Arnold’s cleaned notebooks. Suggestion: use nbviewer (or Colab) when reading the notebooks, rather than GitHub.

  • fast.ai course lesson videos

• Review the end-of-chapter questions at aiquizzes

• Fast.ai community resources:

  • the Fast.ai forums and Discord

  • https://www.cognitivefactory.fr/fastaidocs/

  • https://walkwithfastai.com/

• Connect with a broader AI community at https://twimlai.com/community/

• Helpful references

  • git

    • GitHub’s Git Handbook

  • Jupyter Notebook

    • Appendix from our book
    • tips and tricks

  • Google Colab (intro, overview). Tips:

    • Press Ctrl-Shift-P to open the Command Palette. Lots of useful stuff there; try the “scratch code cell”.
    • Click the down arrow next to the RAM/Disk meter in the toolbar (where it used to say “Connect”) and select “show executed code history”

• Training Tips

  • https://huggingface.co/blog/simple-considerations

  • http://josh-tobin.com/assets/pdf/troubleshooting-deep-neural-networks-01-19.pdf

  • A Recipe for Training Neural Networks

  • https://blog.floydhub.com/training-neural-nets-a-hackers-perspective/

• Tools

  • RunwayML (very high-level interface)

  • Streamlit

  • WandB (experiment tracking)

Keeping up with AI

Tech

• TWIML – podcast, blog
• Papers With Code (sign up for the newsletter)
• Two Minute Papers YouTube channel
• Morning Paper blog
• Arxiv-Sanity (but still insane)
• distill.pub
• Harvard Data Science Review

Ethics / Society

• Fast.AI Data Ethics course
• Montreal AI
• AI Now Institute
• Data and Society
• The Oxford Handbook of Ethics of AI
• AlgorithmWatch
• Harvard BKC
• ACM Conference on Fairness, Accountability, and Transparency (FAccT)

Videos / Podcasts / … that others have liked

• 3Blue1Brown Neural Network Videos
• “Advice on getting started in deep learning” by Andrew Ng

Our General Reflection Questions

As we look at several different technologies throughout this semester, we will ask some of the same questions about each of them. Here’s the list so far. You don’t need to specifically engage them for this activity, but they may be helpful for prompting your thinking:

• How does it work?

• What resources does it need? What resources does it produce?

• What value does it produce for an organization that uses it?

• Besides its primary use, what are other consequences (within and outside the organization) of its deployment? Think of people affected, resources consumed or produced, value generated, etc.

• What are comparable or alternative non-AI products / technologies? What are real-world analogies for this technology (in terms of purpose or function)?

• What ways of looking at or thinking about people does it emphasize? De-emphasize?

• What are its limitations? Which limitations are most fundamental?