Hacker News new | past | comments | ask | show | jobs | submit login

I agree. ML is best explained not from a CS angle but from a maths/physics/biology angle, starting with a Single Layer Perceptron. It's possible to explain the idea of feed-forward/backpropagation computation visually without having to dive into the math of matrix multiplication, and certainly in isolation from other CompSci theory.

Personally I've found this approach, in combination with a visual explainer like the Tensorflow Playground, really effective in getting people to 'get it'. I know it doesn't even begin to cover the breadth of today's ML techniques, but as a conceptual introduction that requires little to no CompSci foundation, it works and it's a start.




Re getting people to get it, 3blue1brown has a fantastic series that feels like:

>It's possible to explain the idea of feed-forward/backpropagation computation visually without having to dive into the math of matrix multiplication, and certainly in isolation from other CompSci theory.

Was a perfect summary of. The visuals are excellent too.[0]

[0]https://youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_...




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: