So, "deep learning" is the idea of doing representation learning via a chain of learned feature extractors. It's all about describing some input data via *deep hierarchies of features*, where features are *learned*. A further question is then: is the brain "deep learning"?
-
-
I would add that our current understanding and usage of modern deep learning -- its genealogy -- lies mostly in earlier modern machine learning techniques, not in neuroscience. The influence of neuroscience has been one of high-level conceptual inspiration, not direct emulation.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Reading about https://en.m.wikipedia.org/wiki/Lateral_geniculate_nucleus … I can say that a part of it is in form of layers, and it computes much more than the first layers of any DL arch. And it not even the brain... Same for V1 cortex. But the great difference is that the brain processes a *stream of information*
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
"is the brain "deep learning"?" ... "my gut feeling is that the brain is generally not DL" ... kind of funny, if you "think" about it.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.