Deep symbolic regression for recurrent sequences

Re:Deep symbolic regression for recurrent sequences by ShamelessC on Sunday January 30, 2022 @04:15PM (#30141172)

tl;dr - They model operations (e.g. multiply, add, cosine, sqrt) as tokens, and use a transformer to predict a recursive function from (incomplete) integer sequences (and float sequences, separately).

This is not dissimilar from e.g. DALL-E where they model images as NLP-style tokens and use a transformer to predict image tokens (operations, respectively) from text tokens (list of ints/floats, respectively).

This demo lets you interact with the model. Pretty cool stuff. Refreshing to see symbolic problems being tackled with deep learning.

Yannic Kilcher video with one of the authors: https://youtu.be/1HEdXwEYrGM

arxiv: https://arxiv.org/abs/2201.04600

[ Parent | on HN ]

Re:Deep symbolic regression for recurrent sequences by verdverm on Sunday January 30, 2022 @07:58PM (#30143108)

If you find this interesting, my phd work is an interesting read

https://seminars.math.binghamton.edu/ComboSem/worm-chiu.pge_...

It is a deterministic algo for SR that I've always thought would benefit from RL.

The biggest problem is SR research has been and still is the lack of a widely used dataset and reproducible results. There is a researcher who beats everyone's results within a year by publishing to Springer without code or data...

[ Parent | on HN ]

Re:Deep symbolic regression for recurrent sequences by verdverm on Monday January 31, 2022 @01:13AM (#30145134)

Fast Function extraction is another interesting Algo for SR

http://trent.st/ffx/

[ Parent | on HN ]