Neurosymbolic Programming for Science
This work addresses the problem of making AI more interpretable and applicable for scientists across natural and social sciences, but it is incremental as it focuses on identifying gaps rather than presenting new methods.
The paper tackles the challenge of integrating Neurosymbolic Programming (NP) techniques into scientific workflows to accelerate discovery, identifying opportunities and challenges with examples from behavior analysis.
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.