Timezone: »

 
Neurosymbolic Programming for Science
Jennifer J Sun · Megan Tjandrasuwita · Atharva Sehgal · Armando Solar-Lezama · Swarat Chaudhuri · Yisong Yue · Omar Costilla Reyes

@
in AI for Science: Progress and Promises »
Event URL: https://openreview.net/forum?id=MJtzhkSRQr »

Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery across fields. These models combine neural and symbolic components to learn complex patterns and representations from data, using high-level concepts or known constraints. As a result, NP techniques can interface with symbolic domain knowledge from scientists, such as prior knowledge and experimental context, to produce interpretable outputs. Here, we identify opportunities and challenges between current NP models and scientific workflows, with real-world examples from behavior analysis in science. We define concrete next steps to move the NP for science field forward, to enable its use broadly for workflows across the natural and social sciences.

Keywords: machine learning · Domain Knowledge · programming languages · scientists

Author Information

Jennifer J Sun (Caltech)
Megan Tjandrasuwita (Massachusetts Institute of Technology)
Atharva Sehgal (University of Texas at Austin)
Armando Solar-Lezama (MIT)
Swarat Chaudhuri (The University of Texas at Austin)
Yisong Yue (Caltech)
Omar Costilla Reyes (MIT)

More from the Same Authors