Why do CNNs generalize so poorly to small image transformations?

Re:Why do CNNs generalize so poorly to small image transform... by salawat on Monday June 11, 2018 @09:21AM (#17283923)

It isn't just branding though. It is a mathematical representation of a synaptic action potential.

The main difference of course being that you are implementing it in silicon rather than carbon, and having no bloody grammar or conception of how in the heck to explain how 'X set of nodes with Y set of weights with Z activation threshold function'=something useful.

They called them Neural networks for a reason. It's been quite a mystery both on the biology (in terms of gray matter) and computing (in terms of ANN) front why it works at all. But it does.

I think I've read Bellman's work before, but I'll take a look. Thanks for the pointer.

[ Parent | on HN ]

Re:Why do CNNs generalize so poorly to small image transform... by xapata on Monday June 11, 2018 @11:50AM (#17285272)

It's got some loose relationship to action potential, but to a network of neurons? It's a leaky abstraction.

[ Parent | on HN ]

Re:Why do CNNs generalize so poorly to small image transform... by salawat on Monday June 11, 2018 @08:27PM (#17289788)

It's been a while since I've been in the literature (about 7 years to be exact).

Just can't find enough hours in the day to keep on top of the state-of-the-art, and unfortunately the career hasn't budged me in the direction of anywhere I could weasel work on it into my day.

C'est la vie.

[ Parent | on HN ]