Skip to main content
Log in

Scientific discovery, causal explanation, and process model induction

  • Published:
Mind & Society Aims and scope Submit manuscript

Abstract

In this paper, I review two related lines of computational research: discovery of scientific knowledge and causal models of scientific phenomena. I also report research on quantitative process models that falls at the intersection of these two themes. This framework represents models as a set of interacting processes, each with associated differential equations that express influences among variables. Simulating such a quantitative process model produces trajectories for variables over time that one can compare to observations. Background knowledge about candidate processes enables search through the space of model structures and associated parameters to find explanations of time-series data. I discuss the representation of such process models, their use for prediction and explanation, and their discovery through heuristic search, along with their interpretation as causal accounts of dynamic behavior.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Taken from Arvay and Langley (2016)

Fig. 2

Similar content being viewed by others

Notes

  1. This rate is always positive and its values are inherently unobservable, so we can adopt any measurement units that we find convenient.

References

  • Arvay A, Langley P (2016) Selective induction of rate-based process models. In: Proceedings of the 4th annual conference on cognitive systems, Evanston

  • Asgharbeygi N, Bay S, Langley P, Arrigo K (2006) Inductive revision of quantitative process models. Ecol Model 194:70–79

    Article  Google Scholar 

  • Bay SD, Shrager J, Pohorille A, Langley P (2003) Revising regulatory networks: from expression data to linear causal models. J Biomed Inf 35:289–297

    Article  Google Scholar 

  • Bradley E, Easley M, Stolle R (2001) Reasoning about nonlinear system identification. Artif Intell 133:139–188

    Article  Google Scholar 

  • Bradshaw GL, Langley P, Simon HA (1980) Bacon.4: the discovery of intrinsic properties. In: Proceedings of the 3rd biennial conference of the Canadian society for computational studies of intelligence, Victoria, pp 19–25

  • Bridewell W, Langley P (2010) Two kinds of knowledge in scientific discovery. Top Cogn Sci 2:36–52

    Article  Google Scholar 

  • Bridewell W, Bani Asadi N, Langley P, Todorovski L (2005) Reducing overfitting in process model induction. In: Proceedings of the 22nd international conference on machine learning, Bonn, pp 81–88

  • Bridewell W, Langley P, Racunas S, Borrett SR (2006) Learning process models with missing data. In: Proceedings of the 17th European conference on machine learning. Springer, Berlin, pp 557–565

  • Bridewell W, Langley P, Todorovski L, Džeroski S (2008) Inductive process modeling. Mach Learn 71:1–32

    Article  Google Scholar 

  • Cohen S, Hindmarsh A (1996) CVODE: a stiff/nonstiff ODE solver in C. Comput Phys 10:138–43

    Article  Google Scholar 

  • Darwiche A (2009) Modeling and reasoning with Bayesian networks. Cambridge University Press, New York

    Book  Google Scholar 

  • Džeroski S, Todorovski L (1995) Discovering dynamics: from inductive logic programming to machine discovery. J Intell Inf Syst 4:89–108

    Article  Google Scholar 

  • Džeroski S, Todorovski L (eds) (2007) Computational discovery of communicable scientific knowledge. Springer, Berlin

    Google Scholar 

  • Falkenhainer BC, Michalski RS (1986) Integrating quantitative and qualitative discovery: the ABACUS system. Mach Learn 1:367–401

    Google Scholar 

  • Feigenbaum EA, Buchanan BG, Lederberg J (1971) On generality and problem solving: a case study using the DENDRAL program. In: Meltzer B, Michie D (eds) Machine intelligence, vol 6. Edinburgh University Press, Edinburgh

    Google Scholar 

  • Forbus KD (1984) Qualitative process theory. Artif Intell 24:85–168

    Article  Google Scholar 

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

    Google Scholar 

  • Gordon A, Edwards P, Sleeman D, Kodratoff Y (1994) Scientific discovery in a space of structural models: an example from the history of solution chemistry. In: Proceedings of the 16th annual conference of the cognitive science society. Lawrence Erlbaum, Atlanta, pp 381–386

  • Hempel CG (1966) Philosophy of natural science. Prentice-Hall, Englewood Cliffs

    Google Scholar 

  • Iwasaki Y, Simon HA (1986) Causality in device behavior. Artif Intell 29:3–32

    Article  Google Scholar 

  • Iwasaki Y, Simon HA (1994) Causality and model abstraction. Artif Intell 67:143–194

    Article  Google Scholar 

  • King RD, Whelan KE, Jones FM, Reiser PGK, Bryant CH, Muggleton SH, Kell DB, Oliver SG (2004) Functional genomic hypothesis generation and experimentation by a robot scientist. Nature 427:247–252

    Article  Google Scholar 

  • Kocabas S (1991) Conflict resolution as discovery in particle physics. Mach Learn 6:277–309

    Google Scholar 

  • Kokar MM (1986) Determining arguments of invariant functional descriptions. Mach Learn 1:403–422

    Google Scholar 

  • Koza JR, Mydlowec W, Lanza G, Yu J, Keane MA (2001) Reverse engineering of metabolic pathways from observed data using genetic programming. Pac Symp Biocomput 6:434–445

    Google Scholar 

  • Langley P (1979) Rediscovering physics with Bacon.3. In: Proceedings of the 6th international joint conference on artificial intelligence. Morgan Kaufmann, Tokyo, pp 505–507

  • Langley P (1981) Data-driven discovery of physical laws. Cogn Sci 5:31–54

    Article  Google Scholar 

  • Langley P, Arvay A (2015) Heuristic induction of rate-based process models. In: Proceedings of the 29th AAAI conference on artificial intelligence. AAAI Press, Austin, pp 537–544

  • Langley P, Bradshaw GL, Simon HA (1983) Rediscovering chemistry with the BACON system. In: Michalski RS, Carbonell JG, Mitchell TM (eds) Machine learning: an artificial intelligence approach. Morgan Kaufmann, San Mateo

    Google Scholar 

  • Langley P, Simon HA, Bradshaw GL, Żytkow JM (1987) Scientific discovery: computational explorations of the creative processes. MIT Press, Cambridge

    Google Scholar 

  • Langley P, Sanchez J, Todorovski L, Džeroski S (2002a) Inducing process models from continuous data. In: Proceedings of the 19th international conference on machine learning. Morgan Kaufmann, Sydney, pp 347–354

  • Langley P, Shrager J, Saito K (2002b) Computational discovery of communicable scientific knowledge. In: Magnani L, Nersessian NJ, Pizzi C (eds) Logical and computational aspects of model-based reasoning. Kluwer, Dordrecht

    Google Scholar 

  • Langley P, Shiran O, Shrager J, Todorovski L, Pohorille A (2006) Constructing explanatory process models from biological data and knowledge. Artif Intell Med 37:191–201

    Article  Google Scholar 

  • Moulet M (1992) ARC.2: linear regression in Abacus. In: Proceedings of the ML 92 workshop on machine discovery, Aberdeen, pp 137–146

  • Murata T, Mizutani M, Shimura M (1994) A discovery system for trigonometric functions. In: Proceedings of the 20th national conference on artificial intelligence. AAAI Press, Seattle, pp 645–650

  • Nordhausen B, Langley P (1990) A robust approach to numeric discovery. In: Proceedings of the 7th international conference on machine learning. Morgan Kaufmann, Austin, pp 411–418

  • Park C, Bridewell W, Langley P (2010) Integrated systems for inducing spatio-temporal process models. In: Proceedings of the 24th AAAI conference on artificial intelligence. AAAI Press, Atlanta, pp 1555–1560

  • Popper KR (1961) The logic of scientific discovery. Science Editions, New York

    Google Scholar 

  • Schaffer C (1990) Bivariate scientific function finding in a sampled, real-data testbed. Mach Learn 12:167–183

    Google Scholar 

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

    Article  Google Scholar 

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

    Google Scholar 

  • Simon HA (1954) Spurious correlation: a causal interpretation. J Am Stat Assoc 49:467–479

    Google Scholar 

  • Simon HA (1966) Scientific discovery and the psychology of problem solving. In: Colodny R (ed) Mind and cosmos. University of Pittsburgh Press, Pittsburgh

    Google Scholar 

  • Todorovski L, Bridewell W, Langley P (2012) Discovering constraints for inductive process modeling. In: Proceedings of the 26th AAAI conference on artificial intelligence. AAAI Press, Toronto, pp 256–262

  • Todorovski L, Shiran O, Bridewell W, Langley P (2005) Inducing hierarchical process models in dynamic domains. In: Proceedings of the 20th national conference on artificial intelligence. AAAI Press, Pittsburgh, pp 892–897

  • Valdés-Pérez RE (1994) Human/computer interactive elucidation of reaction mechanisms: application to catalyzed hydrogenolysis of ethane. Catal Lett 28:79–87

    Article  Google Scholar 

  • Valdés-Pérez RE (1996) Computer science research on scientific discovery. Knowl Eng Rev 11:57–66

    Article  Google Scholar 

  • Washio T, Motoda H (1997) Discovering admissable models of complex systems based on scale types and identity constraints. In: Proceedings of the 15th international joint conference on artificial intelligence. Morgan Kaufmann, Yokohama, pp 810–817

  • Żytkow JM, Zhu J, Hussam A (1990) Automated discovery in a chemistry laboratory. In: Proceedings of the 8th national conference on artificial intelligence. AAAI Press, Boston, pp 889–894

Download references

Acknowledgements

The research reported here was supported by Grant No. N00014-11-1-0107 from the US Office of Naval Research, which is not responsible for its contents. The results draw on joint work with Adam Arvay, Will Bridewell, Saso Džeroski, Ljupčo Todorovski, and others over years of shared effort on computational scientific discovery.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Pat Langley.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Langley, P. Scientific discovery, causal explanation, and process model induction. Mind Soc 18, 43–56 (2019). https://doi.org/10.1007/s11299-019-00216-1

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11299-019-00216-1

Keywords

Navigation