Re:The limitations of gradient descent as a principle of bra...
by api on Monday June 11, 2018 @08:18AM
(#17283611)
You can if you know what the higher level abstraction is. That kind of thing doesn't work when your learning algorithm doesn't have a programmer / mathematician to babysit it who knows more than it does.
... unless God is sitting there hacking our brains' code in real time to kick us out of local maxima. "Damn it... they're stuck on the mind/body dichotomy again... let me see what happens if I bolt a dimension reduction transform on there and then run another gradient descent on top. Shit now they're worshipping cheese... undo, undo, undo..."
... unless God is sitting there hacking our brains' code in real time to kick us out of local maxima. "Damn it... they're stuck on the mind/body dichotomy again... let me see what happens if I bolt a dimension reduction transform on there and then run another gradient descent on top. Shit now they're worshipping cheese... undo, undo, undo..."