The acceleration of scientific discovery is among the most exciting promises of modern AI. However, algorithms that discover new scientific hypotheses and guide experiments must not only have high performance but also produce interpretable outputs. This makes many of our methods a natural fit for this space.
In particular, with collaborators in behavioral neuroscience, we have been recently working to use our methods in the analysis of animal behavior. Specifically, we have used neurosymbolic program synthesis to discover interpretable classifiers and clusters for behaviors, and models of divergences between different human experts annotating behaviors. In a separate ongoing effort with collaborators in cell biology, we are developing the use of program synthesis in discovering high-performance mechanistic models of RNA splicing.
Interpreting Expert Annotation Differences in Animal Behavior Workshop
In: Larochelle, Hugo; Ranzato, Marc'Aurelio; Hadsell, Raia; Balcan, Maria-Florina; Lin, Hsuan-Tien (Ed.): Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, 2020.