Meta Learning Backpropagation and Improving It

Re:Meta Learning Backpropagation and Improving It by jakobov on Tuesday October 25, 2022 @05:54AM (#33328382)

1) This is by Schmidhuber so take it with an extra grain of salt 2) The experiments were on toy datasets. There is a reason they did not do this on a real dataset.

[ Parent | on HN ]

Re:Meta Learning Backpropagation and Improving It by sva_ on Tuesday October 25, 2022 @06:33AM (#33328653)

> This is by Schmidhuber so take it with an extra grain of salt

What makes you say that?

[ Parent | on HN ]

Re:Meta Learning Backpropagation and Improving It by jimkoen on Tuesday October 25, 2022 @06:44AM (#33328746)

Yes! Spill the tea!

[ Parent | on HN ]

Re:Meta Learning Backpropagation and Improving It by cfcf14 on Tuesday October 25, 2022 @07:16AM (#33328988)

It being from Schmidhuber's lab makes it dramatically more credible, in my views. They've been practically a decade ahead of everybody for ages now from a theoretical point of view.

[ Parent | on HN ]

Re:Meta Learning Backpropagation and Improving It by PartiallyTyped on Tuesday October 25, 2022 @08:16AM (#33329476)

Agreed. I'd go as far as to put Schmidhuber and his lab above the laureates.

[ Parent | on HN ]