Hopfield Networks Is All You Need

Re:Hopfield Networks Is All You Need by aparsons on Saturday May 01, 2021 @02:59PM (#27008836)

I’ve seen a lot of efforts to add a notion of associative memory into neural networks. Have any exciting applications of such architectures been publicised?

[ Parent | on HN ]

Re:Hopfield Networks Is All You Need by truth_ on Saturday May 01, 2021 @03:09PM (#27008923)

Just some days ago researchers from Peking U and Microsoft published a paper[0] saying they can access "knowledge neurons" in pretrained embeddings that will enable "fact editing"[1].

[0]: https://arxiv.org/pdf/2104.08696.pdf

[1]: https://medium.com/syncedreview/microsoft-peking-u-researche...

[ Parent | on HN ]

Re:Hopfield Networks Is All You Need by ilaksh on Saturday May 01, 2021 @03:13PM (#27008959)

I thought that Transformers were a type of associative memory.

[ Parent | on HN ]

Re:Hopfield Networks Is All You Need by SneakyTornado29 on Saturday May 01, 2021 @05:08PM (#27009833)

https://arxiv.org/search/cs?searchtype=author&query=Hochreit...

[ Parent | on HN ]

Re:Hopfield Networks Is All You Need by orange3xchicken on Saturday May 01, 2021 @03:07PM (#27008906)

Relevant paper from Misha Belkin's group https://arxiv.org/abs/1909.12362

[ Parent | on HN ]