Re:A Beginner's Guide to Understanding Convolutional Neural ...
by karpathy on Thursday July 21, 2016 @09:04AM
(#12136540)
A human is very good at one-shot learning but CNNs are actually not too terrible either (and this is also an active area of research, e.g. see http://www.arxiv-sanity.com/1603.05106v2). A human might take advantage of good initialization while CNNs start from scratch. Human might have ~1B images by 5 (CNNs get ~1M) of continuous RGBD video and possibly taking advantage of active learning (while CNNs see disconnected samples, which has its pros and cons, mostly cons). i.e. we're disadvantaged in several respects but still doing quite well.
[ Parent
| on HN ]
Re:A Beginner's Guide to Understanding Convolutional Neural ...
by Cybiote on Thursday July 21, 2016 @10:06AM
(#12136896)
It depends on what we mean by vision. Crows for an example, do the sort of things low level things CNNs are capable of. But for full visual comprehension, they are actively making predictions about physics off a probabilistic world model (learned in part from causal interventions) that feed back into perception.
I've not yet looked carefully into it, but I expect that sort of feedback should drastically reduce the amount of required raw data. Machines might not (at first) get to build predictive models from interactions, but even our best approaches to transfer and multi-task learning are very constrained compared to the free form multi modal integrative learning a parrot is capable of. With very little energy spend.
This is good, it means there are still a lot of exciting things left to work out.