Closing in on how the brain works? Combining DL and classical symbolic computation in a biologically plausible model of cortico-thalamo-cortical circuits (with assumed control signals from the basal ganglia). Heavy (but great) stuff from @AdamMarblestonehttps://www.biorxiv.org/content/early/2018/04/22/304980 …
Please read the paper before drawing such conclusions. We’re not “calling for” supervised learning and we don’t confuse routing with backprop. Paper uses contrastive Hebbian learning. Cortical feedback might well do ~BP though. Happy to address specific technical objections.
-
-
"How thalamic relays might orchestrate SUPERVISED DEEP TRAINING and SYMBOLIC computation in the brain" You don't fool me. The hard truth is that there is no supervised learning in the cortex. It's ridiculous. Symbolic computation is even worse. You people get paid for this?
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.
