Researchers propose faster, more efficient alternatives to backpropagation

Re:Researchers propose faster, more efficient alternatives t... by savant_penguin on Sunday December 20, 2020 @12:56PM (#25488122)

Some people use backpropagation and gradient decent interchangeably. It's really confusing though

[ Parent | on HN ]

Re:Researchers propose faster, more efficient alternatives t... by jhrmnn on Sunday December 20, 2020 @02:07PM (#25488688)

I wouldn’t say it’s confusing—it’s wrong and suggests at the least sloppiness in terminology

[ Parent | on HN ]

Re:Researchers propose faster, more efficient alternatives t... by ethbr0 on Sunday December 20, 2020 @05:00PM (#25489930)

> sloppiness in terminology

venturebeat.com

Not the worst, but we're not talking Nature or Spectrum here.

[ Parent | on HN ]

Re:Researchers propose faster, more efficient alternatives t... by dnautics on Sunday December 20, 2020 @08:47PM (#25491339)

That's bad. There are gradient descent techniques that are feed-forward, and understand the domains where those are appropriate and the domains where backprop is appropriate is I think important, especially as you try to do things like mix machine learning techniques with other differentiable programming strategies.

[ Parent | on HN ]

Re:Researchers propose faster, more efficient alternatives t... by option on Sunday December 20, 2020 @03:37PM (#25489307)

of course it is wrong. One nice thing about math is that thing are defined precisely and back propagation and, say, SGD or Adam are different things

[ Parent | on HN ]