Why can't I find an article (or book or journal) on "Lessons from human brain organization for designing artificial intelligences"? Surely it can't be because there are no such lessons, can it?
It is quite easy to make the case that eg LeCun's vision solutions were generalizations from audio processing to image processing. In practice, we can often use AI models to interpret neuroscience, but we can rarely use neuroscience to predict how to build an AI model.
-
-
Marr's ideas of primarily bottom up vision were influential for the philosophy of cognitive science, but in practice people had to come up with different paradigms to build the current generations of vision systems.
- 9 more replies
New conversation -
-
-
This Tweet is unavailable.
-
I have in the past tried to count the cases of neuro/cogno to AI inspiration. There is certainly a decent list, yet it is not *that* long + the delays are long. Yet I suspect the problem is not AI not listening but that we in neuro are rather bad at coming up with good ideas.
End of conversation
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.