Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery. These models combine neural and symbolic components to learn complex patterns and representations from data, using high-level concepts or known constraints. NP techniques can interface with symbolic domain knowledge from scientists, such as prior knowledge and experimental context, to produce interpretable outputs. We identify opportunities and challenges between current NP models and scientific workflows, with real-world examples from behavior analysis in science: to enable the use of NP broadly for workflows across the natural and social sciences.
@article{arxiv.2210.05050,
title = {Neurosymbolic Programming for Science},
author = {Jennifer J. Sun and Megan Tjandrasuwita and Atharva Sehgal and Armando Solar-Lezama and Swarat Chaudhuri and Yisong Yue and Omar Costilla-Reyes},
journal= {arXiv preprint arXiv:2210.05050},
year = {2022}
}
Comments
Neural Information Processing Systems 2022 - AI for science workshop