Saved in:
Bibliographic Details
Main Authors: d'Ascoli, Stéphane, Renard, Arthur, Papadopoulos, Vassilis, Bengio, Samy, Susskind, Josh, Abbé, Emmanuel
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.12207
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912486405439488
author d'Ascoli, Stéphane
Renard, Arthur
Papadopoulos, Vassilis
Bengio, Samy
Susskind, Josh
Abbé, Emmanuel
author_facet d'Ascoli, Stéphane
Renard, Arthur
Papadopoulos, Vassilis
Bengio, Samy
Susskind, Josh
Abbé, Emmanuel
contents We introduce Boolformer, a Transformer-based model trained to perform end-to-end symbolic regression of Boolean functions. First, we show that it can predict compact formulas for complex functions not seen during training, given their full truth table. Then, we demonstrate that even with incomplete or noisy observations, Boolformer is still able to find good approximate expressions. We evaluate Boolformer on a broad set of real-world binary classification datasets, demonstrating its potential as an interpretable alternative to classic machine learning methods. Finally, we apply it to the widespread task of modeling the dynamics of gene regulatory networks and show through a benchmark that Boolformer is competitive with state-of-the-art genetic algorithms, with a speedup of several orders of magnitude. Our code and models are available publicly.
format Preprint
id arxiv_https___arxiv_org_abs_2309_12207
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Boolformer: Symbolic Regression of Logic Functions with Transformers
d'Ascoli, Stéphane
Renard, Arthur
Papadopoulos, Vassilis
Bengio, Samy
Susskind, Josh
Abbé, Emmanuel
Machine Learning
Logic in Computer Science
We introduce Boolformer, a Transformer-based model trained to perform end-to-end symbolic regression of Boolean functions. First, we show that it can predict compact formulas for complex functions not seen during training, given their full truth table. Then, we demonstrate that even with incomplete or noisy observations, Boolformer is still able to find good approximate expressions. We evaluate Boolformer on a broad set of real-world binary classification datasets, demonstrating its potential as an interpretable alternative to classic machine learning methods. Finally, we apply it to the widespread task of modeling the dynamics of gene regulatory networks and show through a benchmark that Boolformer is competitive with state-of-the-art genetic algorithms, with a speedup of several orders of magnitude. Our code and models are available publicly.
title Boolformer: Symbolic Regression of Logic Functions with Transformers
topic Machine Learning
Logic in Computer Science
url https://arxiv.org/abs/2309.12207