Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

All the linear algebra that is needed for AI is matrix multiplication and broadcasting?

Am I the only one who is baffled by this?



If AI == Neural Networks only, maybe matrix knowledge is enough, but when you start to include NLP, Expert systems, SEarch algorithms such as A*, Minimax, etc. in the AI category, you'll have to know more mathematics..

AI is much more than neural networks!


Even for NN alone, those few operations are not enough. Not only that, but to even understand what the operations that I need directly do, I need far more background knowledge of linear algebra.


Well, if you want to simplify even more then all you really need is optimisation and a sufficiently broad class of functions.


I think they forgot to prepend "to convince the math-phobic you know what you're doing"




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

Search: