[HN Gopher] HMT: Hierarchical Memory Transformer for Long Contex...
___________________________________________________________________
HMT: Hierarchical Memory Transformer for Long Context Language
Processing
Author : jasondavies
Score : 65 points
Date : 2024-05-17 11:19 UTC (11 hours ago)
(HTM) web link (arxiv.org)
(TXT) w3m dump (arxiv.org)
| cs702 wrote:
| Code: https://github.com/OswaldHe/HMT-pytorch
|
| This looks really interesting. I've added the paper to my reading
| list and look forward to playing with the code. I'm curious to
| see what kinds of improvements we can get by agumenting
| Transformers and other generative sequence models with this and
| other mechanisms implementing hierarchical memory.[a]
|
| Shouldn't the authors cite the work by Jeff Hawkins et al at
| Numenta? Hawkins has been proposing AI models with hierarchical
| temporal memory for a long time.[b] I can't help but wonder if
| there is a way, somehow, to incorporate his work and ideas in
| Transformers and other generative sequence models.
|
| We sure live in interesting times!
|
| ---
|
| [a] In the past, I've experimented with mechanisms that add
| memory to Transformers, but never with _hierarchy_.
|
| [b] https://en.wikipedia.org/wiki/Hierarchical_temporal_memory
| anthonyskipper wrote:
| I thought Hawkins's book "On Intelligence" was amazing. It's a
| bit wild how close things have followed to the direction he
| laid out.
___________________________________________________________________
(page generated 2024-05-17 23:01 UTC)