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

That's a multi-year process. Being proficient with TensorFlow and PyTorch is not sufficient to do useful research. I suggest you begin by implementing a neural network from scratch in your favorite programming language. Writing up the code for matrix multiplication, dot product, back propagation, etc. will teach you a lot.


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

Search: