Do we have any idea how they integrate feedback?
-
-
-
Afaik you can approximate individual neurons by eg a small 3 layer ANN.
End of conversation
New conversation -
-
-
This broke my mind.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Maybe individual neurons perform better in some sub-networks than others. The 'reward' results in reinforcement of neuronal firing patterns & of the subnet of which the neuron is a part. It could also be a part of a zillion other sub-networks.https://youtu.be/WDoeOuxiReQ
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Do you have some name/reference for that mechanism? I have been intrigued by this since you made an off hand remark about it in your 35c3 talk, but I don't know what to even search for to learn more about it.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Reality is a reinforcement learning fractal
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.