Abstract
Learning and learnability have been long standing topics of interests within the linguistic, computational, and epistemological accounts of inductive inference. Johan van Benthem’s vision of the “dynamic turn” has not only brought renewed life to research agendas in logic as the study of information processing, but likewise helped bring logic and learning in close proximity. This proximity relation is examined with respect to learning and belief revision, updating and efficiency, and with respect to how learnability fits in the greater scheme of dynamic epistemic logic and scientific method.
The research of Nina Gierasimczuk is funded by an Innovational Research Incentives Scheme Veni grant 275-20-043, The Netherlands Organisation for Scientific Research (NWO).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The terms “identifiability”, “learnability”, and “solvability” are often used interchangeably in formal learning theory. Preferring one over the others is usually determined by the wider, often philosophical, methodological, or technical context. “Identifiability” is used in technical contexts, concerned with choosing (identifying) one among many possibilities (e.g., Turing machines or grammars). “Learnability” is a broader quasi-psychological notion often assumed to be (accurately) modelled by identifiability. Finally, “solvability” occurs in more logic-oriented works, and denotes the possibility of deciding on an issue, e.g., whether a hypothesis is true or false. Obviously, the latter can also be viewed as a kind of identifiability.
- 2.
In general some of the proofs require a construction of an appropriate prior plausibility order. For this some classical learning-theoretic concepts and results are used, i.e., locking sequences introduced by Blum and Blum [13], as well as finite tell-tale sets and the simple non-computable version of Angluin’s theorem [2], see also the next section.
- 3.
We will use the name “conclusive learnability” interchangeably with “finite identifiability” which is also sometimes referred to as “identification with certainty”.
- 4.
- 5.
The characterisation involving designated propositional letters can be replaced with one that uses nominals as markers of bottom nodes. For such an approach see Dégremont and Gierasimczuk [16].
- 6.
For more complex actions performed on plausibility models in the context of the comparison between dynamic doxastic and doxastic temporal logic see van Benthem and Dégremont [11].
- 7.
Hintikka took, from the very beginning, the axioms of epistemic logic to describe a strong kind of agent rationality.
References
Alchourrón CE, Gärdenfors P, Makinson D (1985) On the logic of theory change: partial meet contraction and revision functions. J Symb Logic 50(2):510–530
Angluin D (1980) Inductive inference of formal languages from positive data. Inf Control 45(2):117–135
Balbach FJ, Zeugmann T (2009) Recent developments in algorithmic teaching. In: Dediu AH, Ionescu AM, Martín-Vide C (eds) LATA’09: Proceedings of 3rd International Conference on Language and Automata Theory and Applications, Tarragona, Spain, 2–8 April 2009. Lecture Notes in Computer Science, vol 5457. Springer, The Netherlands, pp 1–18
Baltag A, Gierasimczuk N, Smets S (2011) Belief revision as a truth-tracking process. In: Apt K (ed) TARK’11: Proceedings of the 13th Conference on Theoretical Aspects of Rationality and Knowledge, Groningen, The Netherlands, 12–14 July 2011. ACM, New York, pp 187–190
Baltag A, Smets S (2009) Learning by questions and answers: from belief-revision cycles to doxastic fixed points. In: Ono H, Kanazawa M, Queiroz R (eds) WoLLIC’09: Proceedings of 16th International Workshop on Logic, Language, Information and Computation, Tokyo, Japan, 21–24 June 2009. Lecture Notes in Computer Science, vol 5514. Springer, The Netherlands, pp 124–139
van Benthem J (2003) Logic and the dynamics of information. Minds Mach 13(4):503–519
van Benthem J (2006) One is a lonely number: on the logic of communication. In: Chatzidakis Z, Koepke P, Pohlers W (eds) LC’02: Proceedings of Logic Colloquium 2002. Lecture Notes in Logic, vol 27. ASL & A.K. Peters, Cergy-Pontoise, pp 96–129
van Benthem J (2007) Dynamic logic for belief revision. J Appl Non-Classical Logics 2: 129–155
van Benthem J (2007) Rational dynamics and epistemic logic in games. Int Game Theory Rev 9(1):13–45
van Benthem J (2011) Logical dynamics of information and interaction. Cambridge University Press, Cambridge
van Benthem J, Dégremont C (2010) Bridges between dynamic doxastic and doxastic temporal logics. In: Bonanno G, Löwe B, van der Hoek W (eds) LOFT’08: Revised selected papers of 8th Conference on Logic and the Foundations of Game and Decision Theory. Lecture Notes in Computer Science, vol 6006. Springer, New York, pp 151–173
van Benthem J, Gerbrandy J, Hoshi T, Pacuit E (2009) Merging frameworks for interaction: DEL and ETL. J Philos Logic 38(5):491–526
Blum L, Blum M (1975) Toward a mathematical theory of inductive inference. Inf Control 28:125–155
Boutilier C (1993) Revision sequences and nested conditionals. IJCAI’93: Proceedings of the 13th International Joint Conference on Artificial Intelligence. Chambery, France, pp 519–525
Darwiche A, Pearl J (1997) On the logic of iterated belief revision. Artif Intell 89:1–29
Dégremont C, Gierasimczuk N (2009) Can doxastic agents learn? On the temporal structure of learning. In: He X, Horty J, Pacuit E (eds) LORI 2009: Proceedings of Logic, Rationality, and Interaction, 2nd International Workshop, Chongqing, China, 8–11 Oct 2009. Lecture Notes in Computer Science, vol 5834. Springer, Berlin, pp 90–104
Dégremont C, Gierasimczuk N (2011) Finite identification from the viewpoint of epistemic update. Inf Comput 209(3):383–396
Emerson EA, Halpern JY (1986) “Sometimes” and “not never” revisited: on branching versus linear time temporal logic. J ACM 33(1):151–178
Fagin R, Halpern JY, Moses Y, Vardi MY (1995) Reasoning about knowledge. MIT Press, Cambridge
Gärdenfors P (1988) Knowledge in flux-modelling the dynamics of epistemic states. MIT Press, Cambridge
Gierasimczuk N (2009) Bridging learning theory and dynamic epistemic logic. Synthese 169(2):371–384
Gierasimczuk N (2010) Knowing one’s limits. Logical analysis of inductive inference. PhD thesis, Universiteit van Amsterdam, The Netherlands
Gierasimczuk N, de Jongh D (2013) On the complexity of conclusive update. Comput J 56(3):365–377
Gierasimczuk N, Kurzen L, Velázquez-Quesada FR (2009) Learning and teaching as a game: a sabotage approach. In: He X et al. (eds) LORI 2009: Proceedings of Logic, Rationality, and Interaction, 2nd International Workshop, Chongqing, China, 8–11 Oct 2009. Lecture Notes in Computer Science, vol 5834. Springer, Berlin, pp 119–132
Gold EM (1967) Language identification in the limit. Inf Control 10:447–474
Goldszmidt M, Pearl J (1996) Qualitative probabilities for default reasoning, belief revision, and causal modeling. Artif Intell 84:57–112
Hendricks V (2003) Active agents. J Logic Lang Inf 12(4):469–495
Hendricks VF (2001) The convergence of scientific knowledge: a vew from the limit. Kluwer Academic Publishers, Dordrecht
Hendricks VF (2007) Mainstream and formal epistemology. Cambridge University Press, New York
Hintikka J (1962) Knowledge and belief: an introduction to the logic of the two notions. Cornell University Press, Cornell
Jain S, Osherson D, Royer JS, Sharma A (1999) Systems that learn. MIT Press, Chicago
Kelly KT (1998a) Iterated belief revision, reliability, and inductive amnesia. Erkenntnis 50: 11–58
Kelly KT (1998b) The learning power of belief revision. TARK’98: Proceedings of the 7th Conference on Theoretical Aspects of Rationality and Knowledge. Morgan Kaufmann Publishers, San Francisco, pp 111–124
Kelly KT (2004) Learning theory and epistemology. In: Niiniluoto I, Sintonen M, Smolenski J (eds) Handbook of epistemology. Kluwer, Dordrecht (Reprinted. In: Arolo-Costa H, Hendricks VF, van Benthem J (2013) A formal epistemology reader. Cambridge University Press, Cambridge)
Kelly KT, Schulte O, Hendricks V (1995) Reliable belief revision. Proceedings of the 10th International Congress of Logic, Methodology, and Philosophy of Science. Kluwer Academic Publishers, Dordrecht, pp 383–398
Lange S, Zeugmann T (1992) Types of monotonic language learning and their characterization. COLT’92: Proceedings of the 5th Annual ACM Conference on Computational Learning Theory, Pittsburgh, 27–29 July 1992. ACM, New York, pp 377–390
Lehrer K (1965) Knowledge, truth and evidence. Analysis 25(5):168–175
Lehrer K (1990) Theory of knowledge. Routledge, London
Martin E, Osherson D (1997) Scientific discovery based on belief revision. J Symb Logic 62(4):1352–1370
Martin E, Osherson D (1998) Elements of scientific inquiry. MIT Press, Cambridge
van der Meyden R, Wong K (2003) Complete axiomatizations for reasoning about knowledge and branching time. Studia Logica 75(1):93–123
Mukouchi Y (1992) Characterization of finite identification. In: Jantke K (ed) AII’92: Proceedings of the International Workshop on Analogical and Inductive Inference, Dagstuhl castle, Germany, 5–9 Oct 1992. Lecture Notes in Computer Science, vol 642. Springer, Berlin, pp 260–267
Nayak AC (1994) Iterated belief change based on epistemic entrenchment. Erkenntnis 41(3):353–390
Osherson D, Stob M, Weinstein S (1986) Systems that learn. MIT Press, Cambridge
Parikh R, Ramanujam R (2003) A knowledge based semantics of messages. J Logic Lang Inf 12(4):453–467
Plaza J (1989) Logics of public communications. In: Emrich M, Pfeifer M, Hadzikadic M, Ras Z (eds) Proceedings of the 4th International Symposium on Methodologies for Intelligent Systems. Springer, New York, pp 201–216
Putnam H (1975) ‘Degree of Confirmation’ and inductive logic, vol 1, chap 17. Cambridge University Press, Cambridge (Reprinted. In: Schilpp PA (ed) (1999) The philosophy of Rudolf Carnap. Library of living philosophers, vol 11)
Spohn W (1988) Ordinal conditional functions: a dynamic theory of epistemic states. In: Skyrms B, Harper WL (eds) Causation in decision, belief change, and statistics, vol II. Kluwer, Dordrecht
Stalnaker R (2009) Iterated belief revision. Erkenntnis 70(2):189–209
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Gierasimczuk, N., Hendricks, V.F., de Jongh, D. (2014). Logic and Learning. In: Baltag, A., Smets, S. (eds) Johan van Benthem on Logic and Information Dynamics. Outstanding Contributions to Logic, vol 5. Springer, Cham. https://doi.org/10.1007/978-3-319-06025-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-06025-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-06024-8
Online ISBN: 978-3-319-06025-5
eBook Packages: Humanities, Social Sciences and LawPhilosophy and Religion (R0)