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

> I am thinking of two things in particular that current ML approaches lack; that are ubiquitous (well arguably for the second...) in neuroscience: feedback and modeling uncertainty

You'll be interested in a recent post about a new paper for an AI physicist then: https://news.ycombinator.com/item?id=18381827

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