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

PAC learning is compression.

PAC learnable, Finite VC dimensionality, and the following form of compression are fully equivalent.

https://arxiv.org/abs/1610.03592

Basically each individual neuron/perceptron just splits a space into two subspaces.



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

Search: