, Volume 16, Issue 1–2, pp 165–214 | Cite as

Ontologies and Worlds in Category Theory: Implications for Neural Systems

  • Michael John Healy
  • Thomas Preston Caudell


We propose category theory, the mathematical theory of structure, as a vehicle for defining ontologies in an unambiguous language with analytical and constructive features. Specifically, we apply categorical logic and model theory, based upon viewing an ontology as a sub-category of a category of theories expressed in a formal logic. In addition to providing mathematical rigor, this approach has several advantages. It allows the incremental analysis of ontologies by basing them in an interconnected hierarchy of theories, with an operation on the hierarchy that expresses the formation of complex theories from simple theories that express first principles. Another operation forms abstractions expressing the shared concepts in an array of theories. The use of categorical model theory makes possible the incremental analysis of possible worlds, or instances, for the theories, and the mapping of instances of a theory to instances of its more abstract parts. We describe the theoretical approach by applying it to the semantics of neural networks.


category cognition colimit functor limit natural transformation neural network semantics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Adamek, J., H. Herrlich and G. Strecker: 1990, Abstract and Concrete Categories: The Joy of Cats, Cambridge University Press.Google Scholar
  2. Andrews, P. B.: 1986, An Introduction to Mathematical Logic and Type Theory: To Truth through Proof, Academic Press, Inc.Google Scholar
  3. Andrews, R., Diederich, J., Tickle, A. B. 1995‘Survey and Critique of Techniques for Extracting Rules from Trained Artificial Neural Networks’Knowledge-Based Systems8373389CrossRefGoogle Scholar
  4. Arbib, M. A. 1987Brains, Machines, and MathematicsSpringerBerlinGoogle Scholar
  5. Bartfai, G.: 1994, ‘Hierarchical Clustering with ART Neural Networks’, in Proceedings of the International Conference on Neural Networks, Orlando, FL, June 28–July 2, 1994.Google Scholar
  6. Bennet, M. K.: 1995, Affine and Projective Geometry, John Wiley and Sons.Google Scholar
  7. Carpenter, G. A., Tan, A.-H. 1995‘Rule Extraction: From Neural Architecture to Symbolic Representation’Connection Science7327Google Scholar
  8. Craven, M. W. and J. W. Shavlik: 1993, ‘Learning Symbolic Rules using Artificial Neural Networks’, in Proceedings of the 10th International Machine Learning Conference, Amherst, MA, Morgan Kaufmann.Google Scholar
  9. Crole, R. L.: 1993, Categories for Types, Cambridge University Press.Google Scholar
  10. Damasio, A 1989‘Time-Locked Multiregional Retroactivation: A Systems-Level Proposal for the Neural Substrates of Recall and Recognition’Cognition332562CrossRefGoogle Scholar
  11. Ehresmann, A. C., Vanbremeersch, J.-P. 1997‘Information Processing and Symmetry-Breaking in Memory Evolutive Systems’BioSystems432540CrossRefGoogle Scholar
  12. Fu, L. M.: 1992, ‘A Neural Network for Learning Rule-Based Systems’, in Proceedings of the International Joint Conference on Neural Networks, Baltimore, MD.Google Scholar
  13. Goguen, J. A., Burstall, R. M. 1992‘Institutions: Abstract Model Theory for Specification and Programming’Journal of the Association for Computing Machinery3995146Google Scholar
  14. Gruber, T. and G. Olsen: 1994, ‘An Ontology for Engineering Mathematics’, in Proceedings of the Fourth International Conference on Principles of Knowledge Representation and Reasoning, Morgan Kauffman.Google Scholar
  15. Gust, H. and K.-U. Kühnberger: 2005, ‘Learning Symbolic Inferences with Neural Networks’, in Proceedings of the XXVII Annual Conference of the Cognitive Science Society (CogSci2005), Stresa, Italy, Cognitive Science Society, ed. offices University of Indiana, Bloomington, IN.Google Scholar
  16. Healy, M. J 1999a‘A Topological Semantics for Rule Extraction with Neural Networks’Connection Science1191113CrossRefGoogle Scholar
  17. Healy, M. J. 1999b‘Colimits in Memory: Category Theory and Neural Systems’Boswell, J. S. eds. Proceedings of IJCNN’99: International Joint Conference on Neural NetworksIEEE PressWashington, DCGoogle Scholar
  18. Healy, M. J. 2000‘Category Theory Applied to Neural Modeling and Graphical Representations’Gori, M.Amari, S. -I.Giles, C. L.Piuri, V. eds. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks: IJCNN2000IEEE Computer Society PressComo, ItalyGoogle Scholar
  19. Healy, M. J., Caudell, T. P. 1997‘Acquiring Rule Sets as a Product of Learning in a Logical Neural Architecture’IEEE Transactions on Neural Networks8461474CrossRefGoogle Scholar
  20. Healy, M. J. and T. P. Caudell: 2001, ‘A Categorical Semantic Analysis of ART Architectures’, in IJCNN’01:International Joint Conference on Neural Networks, Washington, DC, IEEE Press.Google Scholar
  21. Healy, M. J. and T. P. Caudell: 2002, ‘Aphasic Compressed Representations: A Functorial Semantic Design Principle for Coupled ART Networks’, in The 2002 International Joint Conference on Neural Networks (IJCNN’02), Honolulu, (CD-ROM Proceedings), IEEE Press.Google Scholar
  22. Healy, M. J. and T. P. Caudell: 2003, ‘From Categorical Semantics to Neural Network Design’, in The Proceedings of the IJCNN 2003 International Joint Conference on Neural Networks, Portland, OR, 2003 (CD-ROM Proceedings), IEEE Press.Google Scholar
  23. Healy, M. J. and T. P. Caudell: 2004, Neural Networks, Knowledge, and Cognition: A Mathematical Semantic Model Based upon Category Theory. Technical Report EECE-TR-04-020, Department of Electrical and Computer Engineering, University of New Mexico.Google Scholar
  24. Healy, M. and K. Williamson: 2000, ‘Applying Category Theory to Derive Engineering Software from Encoded Knowledge’, in Proceedings of the Algebraic Methodology and Software Technology 8th International Conference, AMAST 2000, Iowa City, IA. Published in Lecture Notes in Computer Science, Springer-Verlag.Google Scholar
  25. Hebb, D. O. 1949The Organization of BehaviorJohn Wiley and SonsNew YorkGoogle Scholar
  26. Heileman, G. L., M. Georgiopoulos, M. J. Healy and S. J. Verzi: 1997, ‘The Generalization Capabilities of ARTMAP’, in Proceedings of the International Joint Conference on Neural Networks (ICNN97), Houston, TX.Google Scholar
  27. Hirsch, J., Moreno, D. R., Kim, K. H. S. 2001‘Interconnected Large-Scale Systems for Three Fundamental Cognitive Tasks Revealed by Functional mri’Journal of Cognitive Neuroscience13389405CrossRefGoogle Scholar
  28. Jullig, R. and Y. V. Srinivas: 1993, ‘Diagrams for Software Synthesis’, in Proceedings of KBSE ‘93: The Eighth Knowledge-Based Software Engineering Conference, IEEE Computer Society Press.Google Scholar
  29. Kasabov, N. K 1996‘Adaptable Neuro Production Systems’Neurocomputing1395117CrossRefGoogle Scholar
  30. Kelley, W. M., Macrae, C. N., Wyland, C. L., Caglar, S., Inati, S., Heatherton, T. F. 2002‘Finding the Self ? An Event-Related fmri Study’Journal of Cognitive Neuroscience14785794CrossRefGoogle Scholar
  31. Lawvere, F. W. and S. H. Schanuel: 1997, Conceptual Mathematics: A First Introduction to Categories, Cambridge University Press.Google Scholar
  32. Mac Lane, S.: 1971, Categories for the Working Mathematician, Springer. This is the standard reference for mathematicians, written by one of the two co-discoverors of category theory (S. Eilenberg being the other).Google Scholar
  33. McClelland, J. L., D. E. Rumelhart and G. E. Hinton: 1986, ‘The Appeal of Parallel Distributed Processing’, in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1, The MIT Press, pp. 3–44. This volume contains an exposition on bias nodes as a neural mechanism for varying the thresholds of a layer of nodes.Google Scholar
  34. McCullough, W. S., Pitts, W. 1943‘A Logical Calculus of the Ideas Immanent in Nervous Activity’Bulletin of Mathematical Biophysics5115133Google Scholar
  35. Meseguer, J.: 1989, ‘General logics’, in Logic Colloquium ’87, Science Publishers B. V. (North-Holland), pp. 275–329.Google Scholar
  36. Mitra, S., Pal, S. K. 1995‘Fuzzy Multi-Layer Perceptron, Inferencing and Rule Generation’IEEE Transactions on Neural Networks65163CrossRefGoogle Scholar
  37. Otto, I., Grandguillaume, P., Boutkhil, L., Burnod, Y., Guigon, E. 1992‘Direct and Indirect Cooperation between Temporal and Parietal Networks for Invariant Visual Recognition’Journal of Cognitive Neuroscience43557Google Scholar
  38. Perry, C 1999‘Testing a Computational Account of Category-Specific Deficits’Journal of Cognitive Neuroscience11312320CrossRefGoogle Scholar
  39. Pierce, B. C.: 1991, Basic Category Theory for Computer Scientists, MIT Press.Google Scholar
  40. Pinkas, G 1995‘Reasoning, Nonmonotonicity and Learning in Connectionist Networks that Capture Propositional Knowledge’Artificial Intelligence77203247CrossRefGoogle Scholar
  41. Rao, S. C., Ranier, G., Miller, E. K. 1997‘Integration of What and Where in the Primate Prefrontal Cortex’Science276821824Google Scholar
  42. Riesenhuber, M., Poggio, T. 1999‘Are Cortical Models Really Bound by the Binding Problem?’Neuron248793CrossRefGoogle Scholar
  43. Rosen, R 1958a‘A Relational Theory of Biological Systems’Bulletin of Mathematical Biophysics20245260Google Scholar
  44. Rosen, R 1958b‘The Representation of Biological Systems from the Standpoint of the Theory of Categories’Bulletin of Mathematical Biophysics20317341Google Scholar
  45. Sima, J 1995‘Neural Expert Systems’Neural Networks8261271Google Scholar
  46. Squire, L. R., Zola-Morgan, S. 1991‘The Medial Temporal Lobe Memory System’Science25313801385Google Scholar
  47. Srinivas, Y. V. and R. Jullig: 1995, ‘SpecwareTM: Formal Support for Composing Software’, in Proceedings of the Conference of Mathematics of Program Construction.Google Scholar
  48. Stoltenberg-Hansen, V., I. Lindstroem, and E. R. Griffor: 1994, Mathematical Theory of Domains, Cambridge University Press.Google Scholar
  49. Tse, T. H.: 1991, A Unifying Framework for Structured Analysis and Design Models: An Approach using Initial Algebra Semantics and Category Theory, Cambridge University Press.Google Scholar
  50. Vickers, S.: 1993, Topology via Logic, Cambridge University Press.Google Scholar
  51. Wickelgren, I 1997‘Getting a Grip on Working Memory’Science27515801582Google Scholar
  52. Williamson, K. and M. Healy: 1997, ‘Formally Specifying Engineering Design Rationale’, in Proceedings of the Automated Software Engineering Conference-1997.Google Scholar
  53. Williamson, K., Healy, M. 2000‘Deriving Engineering Software from Requirements’Journal of Intelligent Manufacturing11328CrossRefGoogle Scholar
  54. Williamson, K., Healy, M., Barker, R. 2001‘Industrial Applications of Software Synthesis via Category Theory-Case Studies using SpecwareTMAutomated Software Engineering8730CrossRefGoogle Scholar

Copyright information

© Springer 2006

Authors and Affiliations

  • Michael John Healy
  • Thomas Preston Caudell

There are no affiliations available

Personalised recommendations