AUTHORS: Dmitry Zaitsev, Natalia Zaitseva
Download as PDF
ABSTRACT: This paper addresses the problem of formal representation of categorization and concept learning from logical perspective. That way, we construct functional calculus of concepts (FCC) as a natural deduction system enriched with subscripts and type assignments and based on identity. The idea of this presentation stems from our previous research in areas of Intentional Theory of Concepts and formal consideration of Aristotel’s paradeigma (example). The first section clarifies the motivation and briefly outlines the guiding ideas of our approach in the broader context of related work. The second section starts with the discussion of Aristotel’s ideas of example-based reasoning in connection with first principle grasping. We consider some relevant modern findings to support the claim that categorization and concept learning are based on identity rather then on similarity and comparison. That is the third section, which introduces the very functional calculus of concepts formalizing that way an Aristotelian paradeigma as a procedure of new concepts formation. The conclusion contains closing remarks and indicates directions for future work.
KEYWORDS: concept learning, categorization, natural deduction, identityREFERENCES:
1] C. Aggarwal, Instance-Based Learning: A Survey, In: Aggarwal, C. C. (ed.) Data classification: algorithms and applications, CRC press,
2014, pp. 157-185.
 A. Beavers, Phenomenology and artificial intelligence, Metaphilosophy. 33(1-2), 2002, pp. 70- 82.
 S. Boriah, V. Chandola and V. Kumar, Similarity measures for categorical data: A comparative evaluation. In: Proceedings of the 2008 SIAM international conference on data mining, Society for Industrial and Applied Mathematics 2008, pp. 243-254.
 F. Botana, A fuzzy measure of similarity for instance-based learning. In: International Symposium on Methodologies for Intelligent Systems, Springer, Berlin–Heidelberg 1999, pp. 439-447.
 R. Chrisley, Embodied artificial intelligence, Artificial intelligence 149(1), 2003, pp. 131-150.
 J. Clapper, Graded similarity in free categorization, Cognition 190, 2019, pp. 1-19.
 H. Dreyfus, What computers can’t do: A Critique of Artificial Reason, New York: Harper and Row 1972.
 T. Froese and T. Ziemke, Enactive artificial intelligence: Investigating the systemic organization of life and mind, Artificial Intelligence 173(3-4), 2009, pp. 466-500.
 E. Keogh, Instance-Based Learning. In: Sammut C., Webb G.I. (eds.) Encyclopedia of Machine Learning Springer, Boston, MA 2011, pp. 549- 550.
 N. Lachiche and P. Marquise, Scope classification: An instance-based learning algorithm with a rule-based characterisation. In: European Conference on Machine Learning Springer, Berlin– Heidelberg 1998, pp. 268-279.
 B. Lake, R. Salakhutdinov and J. Tenenbaum, Human-level concept learning through probabilistic program induction, Science 350(6266), 2015, pp. 1332-1338.
 B. Lake, T. Ullman, J. Tenenbaum and S. Gershman, Building machines that learn and think like people, Behavioral and brain sciences 40, 2017, pp. 1-72.
 R. Manzotti, Embodied AI beyond Embodied Cognition and Enactivism, Philosophies 4(3), 2019, p. 39.
 A. Martinho and A. Kacelnik, Ducklings imprint on the relational concept of “same or different”, Science 353 (6296), 2016, pp. 286-288.
 A. Morgan and G. Piccinini,Towards a cognitive neuroscience of intentionality, Minds and Machines 28(1), 2018, pp. 119-139.
 D. Munch, The Early Work of Husserl and Arti- ¨ ficial Intelligence, Journal of the British Society for Phenomenology 21(2), 1990, pp. 107-120.
 N. Said, M. Engelhart, C. Kirches, S. Korkel ¨ and D. Holt, Applying mathematical optimization methods to an ACT-R instance-based learning model, PloS one 11(7), 2016, e0158832.
 W. Quine, Natural kinds. In: Essays in honor of Carl G. Hempel Springer, Dordrecht 1969, pp. 5-23.
 L. Rips, Similarity, typicality, and categorization. In: Vosniadou S., Ortony A. (eds.) Similarity and analogical reasoning Cambridge University Press 1989, pp. 21-59.
 C. ten Cate, The comparative study of grammar learning mechanisms: birds as models, Current opinion in behavioral sciences 21, 2018, pp. 13- 18.
 E. Versace, A. Martinho-Truswell, A. Kacelnik and G. Vallortigara, Priors in animal and artificial intelligence: where does learning begin?, Trends in cognitive sciences 22(11), 2018, pp. 963-965.
 M. Wrathall and S. Kelly, Existential phenomenology and cognitive science, The Electronic Journal of Analytic Philosophy 4 1996.
 D. Zaitsev and N. Zaitseva, Categorization in intentional theory of concepts. In: International Symposium on Neural Networks, Lecture Notes in Computer Science 9719, 2016, pp. 465–473.
 D. Zaitsev and N. Zaitseva,Calculus of concepts, Tomsk State University Journal of Philosophy, Sociology and Political Science 49, 2019, pp. 26-33. In Russian
 N. Zaitseva and D. Zaitsev, Phenomenological perspective in modern neuroscience, Russian Journal og Philosophical Sciences 1, 2017, pp. 71–84. In Russian