Yann LeCun, Geoffrey Hinton and Yoshua Bengio win Turing Award

Re:Yann LeCun, Geoffrey Hinton and Yoshua Bengio win Turing ... by amelius on Wednesday March 27, 2019 @03:04PM (#19504730)

And we still don't know if/how biological brains perform backpropagation. Perhaps we should consider calling NNs "weight networks" instead.

[ Parent | on HN ]

Re:Yann LeCun, Geoffrey Hinton and Yoshua Bengio win Turing ... by masko on Thursday March 28, 2019 @04:21PM (#19516196)

Yeah that might be a better name. Sometimes it's called a "computation graph", since that's exactly what it really is. A network of nodes computing weights and derivatives based off inputs and/or outputs.

[ Parent | on HN ]

Re:Yann LeCun, Geoffrey Hinton and Yoshua Bengio win Turing ... by ska on Wednesday March 27, 2019 @03:10PM (#19504797)

That was pretty much hashed out in the 70s when NN interest got going again. I'm not sure there is much value in recapitulating the discussion....

[ Parent | on HN ]

Re:Yann LeCun, Geoffrey Hinton and Yoshua Bengio win Turing ... by erikpukinskis on Wednesday March 27, 2019 @04:59PM (#19505966)

Well, we do have new perspective after 50 years.

Also, there is educational value in conversation.

What is the value to you in shutting down a conversation someone else is interested in having?

At least cite the answer to the question if you feel it's settled scholarship.

[ Parent | on HN ]