“All we have in our heads is big activity vectors that cause more big activity vectors.” Hinton / Aetherial Symbols https://drive.google.com/file/d/0B8i61jl8OE3XdHRCSkV1VFNqTWc/edit …
Available evidence contradicts the assumption that the brain encodes meaning via geometric spaces. Topological spaces are a better candidate.
-
-
Do you follow Numenta's work? Interesting revent paper. https://numenta.com/papers/a-theory-of-how-columns-in-the-neocortex-enable-learning-the-structure-of-the-world/ … Made me think of Hinton's recent paper.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
The PDP group has been following up on that vector space hypothesis for decades -- what evidence is there against this / for topological spaces?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
What is the evidence for this claim,
@fchollet?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.