Fall Symposium on Computational Scientific Discovery

Aims for the Symposium

Scientific discovery has intrigued AI researchers since the 1970s, but excitement about this topic has increased recently, with new contributors from physics, applied mathematics, and other fields joining the movement. Nevertheless, most efforts to date have focused on individual components of discovery. This was a reasonable initial strategy, but the time seems ripe to should move beyond these piecemeal efforts. The expanded agenda should combine not only different forms of discovery, but also other facets of science, including creation of measuring devices, design of controlled experiments, and communication of results.

The Fall Symposium on Integrated Approaches to Computational Scientific Discovery will offer a venue for reporting progress in this important and challenging area. We solicit submissions on topics that include, but are not limited, to:

We also welcome submissions on human-machine teams whose members collaborate to achieve new scientific insights, which raises many of the same issues as the integration of automated systems. We hope that this audacious vision will attract not only AI developers whose work addresses the computational challenges of integrated discovery systems, but also: Together, these participants will offer complementary perspectives on the different components of scientific discovery, how they can interact with each other effectively, and open issues that the community should address in future research.

Schedule and Submissions

The symposium will run two and a half days, from morning on Thursday, November 7, through midday on Saturday, November 9. The meeting will revolve around presentations that report system designs or implementations combining two or more components of scientific research, at least one handled by machine. The event will begin with invited talks that identify different components and examine their interaction in specific fields, along with reviews of previous integrated and human-machine discovery systems.

The remainder of the meeting will comprise presentations by research groups about recent progress on integration efforts, including both results with implemented systems and thoughtful proposals for new approaches or challenges. The symposium will organize sessions around different types of integration, not around methodological paradigms. Rather than focusing on algorithmic details of component algorithms, submissions to the symposium and presentations at the gathering should focus instead on:

Structuring talks in this way should increase communication among researchers with different backgrounds and suggest principles of integration that move beyond specific paradigms. We will apply the same principle to talks on human-machine teaming, asking speakers to state clearly how people communicate with AI modules and vice versa.

Authors should submit abstracts of proposed talks through the AAAI Spring Symposium EasyChair site, along with one or two references and links to papers that are representative of the authors' work on computational discovery. Abstracts should be a full page in 11-point font and need not follow AAAI format.

Submissions are due Friday, August 23, 2024, AoE (Anywhere on Earth). The organizing committee will select abstracts for presentation that report integrated approaches to discovery, with preference given to ones that address the questions listed above. It will also favor research on systems that find laws or models that make contact with existing scientific theories, as well as ones whose findings are stated in established scientific formalisms.

Symposium Organizers


Addis, M., Lane, P. C. R., Sozou, P. D., & Gobet, F. (Eds.). (2019). Scientific discovery in the social sciences. Cham, Switzerland: Springer.

Bridewell, W., Langley, P., Todorovski, L., & Džeroski, S. (2008). Inductive process modeling. Machine Learning, 71, 1–32.

Champion, K.; Lusch, B.; Kutz, J. N.; and Brunton, S. L. 2019. Data-driven discovery of coordinates and governing equations. Proceedings of the National Academy of Sciences, 116, 22445–22451.

Chen, R. T. Q., Rubanova, Y., Bettencourt, J., & Duvenaud, D. K. (2018). Neural ordinary differential equations. Advances in Neural Information Processing Systems 31. Curran Associates.

Cranmer, M., Sanchez-Gonzalez, A., Battaglia, P., et al. (2020). Discovering symbolic models from deep learning with inductive biases. Neural Information Processing Systems 33. Vancouver, Canada.

Džeroski, S., & Todorovski, L. (1995). Discovering dynamics: From inductive logic programming to machine discovery. Journal of Intelligent Information Systems, 4, 89–108.

Džeroski, S., & Todorovski, L. (Eds.). (2007). Computational discovery of scientific knowledge. Berlin: Springer.

Fries, W. D., He, X., & Choi, Y. (2022). LaSDI: Parametric latent space dynamics identification. Computer Methods in Applied Mechanics and Engineering, 399, 115436.

Gil, Y. (2022). Will AI write scientific papers in the future? AI Magazine, 42 (4), 3–15.

Glymour, C., Scheines, R., Spirtes, P., & Kelly, K. (1987). Discovering causal structure: Artificial intelligence, philosophy of science, and statistical modeling. San Diego: Academic Press.

Iten, R., Metger, T., Wilming, H., et al. (2020). Discovering physical concepts with neural networks. Physical Review Letters, 124, 010508.

King, R. D., Whelan, K. E., Jones, F. M., et al. (2004). Functional genomic hypothesis generation and experimentation by a robot scientist, Nature, 427, 247–252.

Kitano, H. (2021). Nobel Turing Challenge: Creating the engine for scientific discovery. npj Systems Biology and Applications, 7, 29.

Langley, P. (1981). Data-driven discovery of physical laws. Cognitive Science, 5, 31–54.

Langley, P. (2000). The computational support of scientific discovery. International Journal of Human-Computer Studies, 53, 393–410.

Langley, P. (2024). Integrated systems for computational scientific discovery. Proceedings of the Thirty-Eighth Annual AAAI Conference on Artificial Intelligence (pp. 22598–22606). Vancouver: AAAI Press.

Langley, P., Simon, H. A., Bradshaw, G. L., & Zytkow, J. M. (1987). Scientific discovery: Computational explorations of the creative processes. Cambridge, MA: MIT Press.

Lenat, D. B. (1977). The ubiquity of discovery. Artificial Intelligence, 9, 257–285.

Lindsay, R. K., Buchanan, B. G., Feigenbaum, E. A., & Lederberg, J. (1980). Applications of artificial intelligence for organic chemistry: The DENDRAL project. New York, NY: McGraw-Hill.

Nordhausen, B., & Langley, P. (1993). An integrated framework for empirical discovery. Machine Learning, 12, 17–47.

Raissi, M., & Karniadakis, G. E. (2018). Hidden physics models: Machine learning of nonlinear partial differential equations. Journal of Computational Physics, 357, 125–141.

Schmidt, M., & Lipson, H. (2009). Distilling free-form natural laws from experimental data. Science, 324, 81–85.

Shrager, J., & Langley, P. (Eds.) (1990). Computational models of scientific discovery and theory formation. San Francisco: Morgan Kaufmann.

Stach, E., DeCost, B., Kusne, A. G. et al. (2021). Autonomous experimentation systems for materials development: A community perspective. Matter, 4, 2702–2726.

Todorovski L. (2011). Equation discovery. In C. Sammut & G. I. Webb (Eds.), Encyclopedia of machine learning. Boston, MA: Springer.

Valdes-Perez, R. E. (1994). Human/computer interactive elucidation of reaction mechanisms: Application to catalyzed hydrogenolysis of ethane. Catalysis Letters, 28, 79–87.

Velasquez, A. (2023). DARPA AIE Program Announcement: Foundation Models for Scientific Discovery. \url{https://sam.gov/opp/dd906dc45ee347d5a0c29d980cf67dcc/}.

Wu, T., & Tegmark, M. (2019). Toward an artificial intelligence physicist for unsupervised learning. Physical Review E, 100, 033311.