Yep - also we have a large tendency to use feedforward NNs right now, but I have... | Hacker News

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

login

gavanwoolery on June 11, 2016 | parent | context | favorite | on: AI, Deep Learning, and Machine Learning: A Primer ...

Yep - also we have a large tendency to use feedforward NNs right now, but I have a sneaking suspicion that the future lies in something closer to recurrent NNs. Or probably something more complex, like automata-ish properties (IIRC there is also some NN that uses Turing-like devices).

eli_gottlieb on June 12, 2016 [–]

Nah. If we want properly humanlike AI software, we're going to have to find a way to make inference in probabilistic programs a lot faster.

Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact