Abstract
Through semiotic modelling, a system can retrieve and manipulate its own representational formats to interpret a series of observations; this is in contrast to information processing approaches that require representational formats to be specified beforehand and thus limit the semantic properties that the system can experience. Our semiotic cognitive automaton is driven only by the observations it makes and therefore operates based on grounded symbols. A best-case scenario for our automaton involves observations that are univocally interpreted—i.e. distinct observation symbols—and that make reference to a reality characterised by “hard constraints”. Arithmetic offers such a scenario. The gap between syntax and semantics is also subtle in the case of calculations. Our automaton starts without any a priori knowledge of mathematical formalisms and not only learns the syntactical rules by which arithmetic operations are solved but also reveals the true meaning of numbers by means of second-order reasoning.









Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
I learned of this use of the extended correlation from the Italian computer scientist Piero Slocovich.
This exception is represented by the regular expressions that contain the impossible sequences “;0”, “=0” and so on, which are already known from the first iteration (see Table 2).
References
Newell A, Simon HA. Computer science as empirical inquiry: symbols and search. Commun ACM. 1976;19:113–26.
Hofstadter D. The ineradicable Eliza effect and its dangers. In Hofstadter D, editor. Fluid concepts and creative analogies: computer models of the fundamental mechanisms of thought. New York: Basic Books; 1994. p. 155–168.
Searle J. Minds, brains and programs. Behav Brain Sci. 1980;3:417–24.
Harnad S. The symbol grounding problem. Phys D. 1990;42:335–46.
Haikonen P. The role of the associative processing in cognitive computation. Cognit Comput. 2009;1:42–9.
Wang P. Experience-grounded semantics: a theory for intelligent systems. Cogn Syst Res. 2005;6(4):282–302.
Ziemke T. Rethinking grounding. In: Riegler MPA, von Stein A, editors. Understanding representation in the cognitive sciences. New York: Kluwer Academic/Plenum Publishers; 1999. p. 177–190.
Devlin KJ. Introduction to mathematical thinking. Palo Alto: Keith Devlin; 2012.
Fetzer JH. Artificial intelligence: its scope and limits. Netherlands: Springer; 1990.
Jackson SA, Sharkey NE. Grounding computational engines. In: Kevitt PMc, editor. Integration of natural language and vision processing. Netherlands: Springer; 1996. p. 167–84.
Gomes A, Gudwin R, El-Hani C, Queiroz J. Towards the emergence of meaning processes in computers from Peircean semiotics. Mind Soc Cogn Stud Econ Soc Sci. 2007;6:173–87.
Meystel A. Multiresolutional semiotic systems. In: Proceedings of the IEEE international symposium on intelligent control/intelligent systems and semiotics; 1999. p. 198–202.
Vogt P. The physical symbol grounding problem. Cogn Syst Res. 2002;3(3):429–57.
Rieger BB. Semiotics and computational linguistics. On semiotic cognitive information processing. In: Zadeh LA, Kacprzyk J, editors. Computing with words in information/intelligent systems. Germany: Heidelberg; 1999. p. 93–118 (Physica).
Bloom B, editor. Taxonomy of educational objectives: book I, cognitive domain. New York: Longman Green; 1956.
Franco L, Cannas SA. Solving arithmetic problems using feed-forward neural networks. Neurocomputing. 1998;18:61–79.
Hoshen Y, Peleg S. Visual learning of arithmetic operations. CoRR, 2015; abs/1506.02264.
Hofstadter D. How Raymond Smullyan inspired my 1112-year-old self. In: Smullyan R, Rosenhouse J, editors. Four lives: a celebration of Raymond Smullyan. New York: Dover Publications; 2014.
Schweizer P. Physical instantiation and the propositional attitudes. Cogn Comput. 2012;4:226–35.
Kazakov D. The self-cognisant robot. Cogn Comput. 2012;4:347–53.
Wang P. Embodiment: Does a laptop have a body? In: Proceedings of AGI conference, Arlington, Virginia, USA; p. 174–179; March 2009.
de Saussure F. Grundfragen der allgemeinen Sprachwissenschaft. Berlin: de Gruyter; 1915. Charles Bally unter Mitw. von Albert Riedlinger, editors, translator Herman Lommel (2001).
Wall L. Perl language reference manual—for Perl version 5.12.1. Network Theory Ltd; 2010.
Burch R. Charles Sanders Peirce. In: Zalta EN, editor. The Stanford encyclopedia of philosophy (Winter 2014 edition). 2014. http://plato.stanford.edu/archives/win2014/entries/peirce/.
Nozawa E. Peircean semeiotic—a 21st century scientific methodology. In: Proceedings of the international symposium on collaborative technologies and systems, Orlando, FL, USA; p. 224–235, May 2007.
Barthes R. Elements of semiology. London: Jonathan Cape, 1964. trans. Lavers A and Smith C (1967).
Rieger BB. Computing fuzzy semantic granules from natural language texts. A computational semiotics approach to understanding word meanings. In: Hamza M, editor. Proceedings of the IASTED international conference on artificial intelligence and soft computing, Honolulu, Hawaii, USA; p. 475–479, August 1999.
Berkhin P. Survey of clustering data mining techniques. Technical report. San Jose: Accrue Software, Inc.; 2002.
Ernest P. A semiotic perspective of mathematical activity: the case of number. Educ Stud Math. 2006;61:67–101.
Goguen J. An introduction to algebraic semiotics, with applications to user interface design. In: Nehaniv C, editor. Computation for metaphor, analogy and agents. New York: Springer Lecture Notes in Artificial Intelligence; 1999. p. 242–291.
Lengnink K, Schlimm D. Learning and understanding numeral systems: semantic aspects of number representations from an educational perspective. In: Löwe B, Müller T, editors. Philosophy of mathematics: sociological aspects and mathematical practice. London: College Publications; 2010. p. 235–264.
Thagard P. Abductive inference: from philosophical analysis to neural mechanisms. In: Feeney A, Heit E, editors. Inductive reasoning: cognitive, mathematical, and neuroscientific approaches. Cambridge: Cambridge University Press; 2007. p. 226–247.
Russell B. The problems of philosophy. Oxford: Oxford University Press; 1959.
Mitchell TM. The need for biases in learning generalizations. In: Shavlik JW, Dietterich TG, editors. Readings in machine learning. Los Altos: Morgan Kauffman; 1980. p. 184–191.
Nasuto SJ, Bishop JM, Roesch EB, Spencer MC. Zombie mouse in a Chinese room. Philos Technol. 2015;28:209–23.
Konderak P. On a cognitive model of semiosis. Stud Log Gramm Rhetor. 2015;40:129–44.
Colton S. Refactorable numbers: a machine invention. J Integer Sequ. 1999;2, Art. ID 99.1.2. http://eudml.org/doc/226761.
D’Ulizia A, Ferri F, Grifoni P. A survey of grammatical inference methods for natural language learning. Artif Intell Rev. 2011;36(1):1–27.
Harris ZS. Distributional structure. Word. 1954;10:146–62.
Lamb SM. On the mechanization of syntactic analysis. In: 1961 Conference on machine translation of languages and applied language analysis, national physical laboratory symposium no. 13, London, Her Majesty’s Stationery Office, 1961. vol. 2, p. 674–685.
Solan Z, Horn D, Ruppin E, Edelman S. Unsupervised learning of natural languages. Proc Natl Acad Sci. 2005;102(33):11629–34.
Ionin T, Matushansky O. The composition of complex cardinals. J Semant. 2006;23:315–60.
Sinatra R, Condorelli D, Latora V. Networks of motifs from sequences of symbols. Phys Rev Lett. 2010;105:178702.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
Valerio Targon declares that he has no conflict of interest
Informed Consent
All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1975, as revised in 2008 (5). Additional informed consent was obtained from all patients for which identifying information is included in this article.
Human and Animal Rights
This article does not contain any studies with human participants or animals performed by the author.
Additional information
The views expressed in this article reflect my personal opinion and not that of the EPO.
Rights and permissions
About this article
Cite this article
Targon, V. Learning the Semantics of Notational Systems with a Semiotic Cognitive Automaton. Cogn Comput 8, 555–576 (2016). https://doi.org/10.1007/s12559-015-9378-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-015-9378-0