Current stage: Entry ML concepts Learned for: 7h Satisfied? Yup

Yesterday, I got no ML work done. Got overwhelmed replying to everyone on here + in dms. Don’t blame me 💀

Started the FastAI course - amazed at how practical it is.

Book highlights so far: “if you regard a neural network as a mathematical function, it turns out to be a function that is extremely flexible depending on its weights. A mathematical proof called the universal approximation theorem shows that this function can solve any problem to any level of accuracy, in theory.”

Positive Feedback Loops:

  1. predictive policing model created from past arrest data reflects existing biases, predicting arrests rather than actual crime
  2. police use this model to focus activity in certain areas, leading to more arrests in those locations
  3. data from these new arrests is used to update and retrain the model, potentially reinforcing biases

beginner stuff, but still fascinating to me.

Early coding sessions are always messy for me. They just remind me how much I don’t know, haha!

Goal for tomorrow is to continue the momentum.