Geoffrey Hinton Watch posted an update
Geoffrey Hinton explains how early neural networks borrowed the idea of strengthening connections between active brain cells, and why that simple rule was not enough.
Why it mattersIn a new interview with The Naked Scientists, he describes backpropagation as a way to work out small adjustments for all a network’s connections at once, rather than testing them one by one. That is the practical trick behind training today’s large networks, in Hinton’s account. A useful bit of AI’s origin story, without requiring anyone to pretend calculus is a light afternoon read.
Discuss: Does explaining AI through the brain make neural networks easier to understand, or risk suggesting they work more like brains than they really do?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.