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

The brain has a lot of skip connections and is massively recurrent. In a sense, the brain can be thought of as having infinite depth due to recurrent thalamno-cortical loops. They do mention thalamno-cortical loops in the paper, so I think a more concrete definition of what is meant by "depth" would be helpful.


The "infinite depth" seems to be a matter of definition. It's practically infinite if you include feedback loops via learning. If you exclude learning, then it's far from "infinite". Activations linger for up to 15-30 seconds, so at oscillations of around 30 Hz that would result in about 450-900 loops (times an unknown small multiplier for the actual number of layers). But the brain presumably only backprops/optimizes a few layers at a time and not much "through" time.


There's also evidence that the brain does optimize through time and might be implementing, at least in some places, algorithms close to LSTD.




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

Search: