Learners Based on Transducers
Conference paper
First Online:
Abstract
As data come out one by one from an infinite stream, automatic learners maintain some string as long term memory, and update it at every new datum (example) they process. Transduced learners are generalization of automatic learners. Both kind of learners are evaluated with respect to the space they consume for learning. For automatic learners, it is unknown whether at any point, the size of the long term memory can be bounded by the length of the longest datum that has been received so far. Here it is shown that, even when restricting learning to automatic families, there is a hierarchy of classes that can be learnt with memory \(O(n^k)\), and all automatic families which are learnable in principle can be learnt by a transduced learner using exponential sized memory.
Keywords
Automata and logic Inductive inference TransducersReferences
- 1.Angluin, D.: Inductive inference of formal languages from positive data. Inf. Control 45, 117–135 (1980)MathSciNetCrossRefMATHGoogle Scholar
- 2.Bārzdiņš, J.: Inductive inference of automata, functions and programs. In: Proceedings of the 20th International Congress of Mathematicians, Vancouver, pp. 455–460 (1974). (in Russian). English translation in American Mathematical Society Translations: Series 2, 109:107–112 (1977)Google Scholar
- 3.Blum, L., Blum, M.: Toward a mathematical theory of inductive inference. Inf. Control 28, 125–155 (1975)MathSciNetCrossRefMATHGoogle Scholar
- 4.Blumensath, A., Grädel, E.: Automatic structures. In: 15th Annual IEEE Symposium on Logic in Computer Science, LICS 2000. pp. 51–62 (2000)Google Scholar
- 5.Case, J., Jain, S., Le, T.D., Ong, Y.S., Semukhin, P., Stephan, F.: Automatic learning of subclasses of pattern languages. In: Dediu, A.-H., Inenaga, S., Martín-Vide, C. (eds.) LATA 2011. LNCS, vol. 6638, pp. 192–203. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21254-3_14 CrossRefGoogle Scholar
- 6.Case, J., Jain, S., Seah, S., Stephan, F.: Automatic functions, linear time and learning. Log. Methods Comput. Sci. 9(3:19), 1–26 (2013)MathSciNetMATHGoogle Scholar
- 7.Case, J., Kötzing, T.: Difficulties in forcing fairness of polynomial time inductive inference. In: Gavaldà, R., Lugosi, G., Zeugmann, T., Zilles, S. (eds.) ALT 2009. LNCS (LNAI), vol. 5809, pp. 263–277. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04414-4_23 CrossRefGoogle Scholar
- 8.Case, J., Lynes, C.: Machine inductive inference and language identification. In: Nielsen, M., Schmidt, E.M. (eds.) ICALP 1982. LNCS, vol. 140, pp. 107–115. Springer, Heidelberg (1982). https://doi.org/10.1007/BFb0012761 CrossRefGoogle Scholar
- 9.Case, J., Smith, C.: Comparison of identification criteria for machine inductive inference. Theor. Comput. Sci. 25, 193–220 (1983)MathSciNetCrossRefMATHGoogle Scholar
- 10.Freivalds, R., Kinber, E., Smith, C.H.: On the impact of forgetting on learning machines. J. ACM 42, 1146–1168 (1995)MathSciNetCrossRefMATHGoogle Scholar
- 11.Gold, E.M.: Language identification in the limit. Inf. Control 10, 447–474 (1967)MathSciNetCrossRefMATHGoogle Scholar
- 12.Hodgson, B.R.: Théories décidables par automate fini. Ph.D. thesis, Département de mathématiques et de statistique, Université de Montréal (1976)Google Scholar
- 13.Jain, S., Luo, Q., Stephan, F.: Learnability of automatic classes. J. Comput. Syst. Sci. 78, 1910–1927 (2012)MathSciNetCrossRefMATHGoogle Scholar
- 14.Jain, S., Ong, Y.S., Pu, S., Stephan, F.: On automatic families. In: Proceedings of the Eleventh Asian Logic Conference, in Honor of Professor Chong Chitat on his Sixtieth Birthday, pp. 94–113. World Scientific (2012)Google Scholar
- 15.Jain, S., Osherson, D.N., Royer, J.S., Sharma, A.: Systems That Learn, 2nd edn. Bradford—MIT Press, Cambridge (1999)Google Scholar
- 16.Khoussainov, B., Nerode, A.: Automatic presentations of structures. In: Leivant, D. (ed.) LCC 1994. LNCS, vol. 960, pp. 367–392. Springer, Heidelberg (1995). https://doi.org/10.1007/3-540-60178-3_93 CrossRefGoogle Scholar
- 17.Khoussainov, B., Nies, A., Rubin, S., Stephan, F.: Automatic structures: richness and limitations. Log. Methods Comput. Sci. 3(2:2), 1–18 (2017)MathSciNetMATHGoogle Scholar
- 18.Kinber, E., Stephan, F.: Language learning from texts: mind changes, limited memory and monotonicity. Inf. Comput. 123, 224–241 (1995)CrossRefMATHGoogle Scholar
- 19.Lange, S., Zeugmann, T., Zilles, S.: Learning indexed families of recursive languages from positive data: a survey. Theor. Comput. Sci. 397, 194–232 (2008)MathSciNetCrossRefMATHGoogle Scholar
- 20.Nivat, M.: Transductions des langages de Chomsky. Annales de l’Institut Fourier, Grenoble 18, 339–455 (1968)MathSciNetCrossRefMATHGoogle Scholar
- 21.Osherson, D., Stob, M., Weinstein, S.: Learning strategies. Inf. Control 53, 32–51 (1982)MathSciNetCrossRefMATHGoogle Scholar
- 22.Osherson, D., Stob, M., Weinstein, S.: Systems That Learn. An introduction to learning theory for cognitive and computer scientists. Bradford—MIT Press, Cambridge (1986)Google Scholar
- 23.Pitt, L.: Inductive inference, DFAs, and computational complexity. In: Jantke, K.P. (ed.) AII 1989. LNCS, vol. 397, pp. 18–44. Springer, Heidelberg (1989). https://doi.org/10.1007/3-540-51734-0_50 CrossRefGoogle Scholar
- 24.Rubin, S.: Automata presenting structures: a survey of the finite string case. Bull. Symb. Log. 14, 169–209 (2008)MathSciNetCrossRefMATHGoogle Scholar
- 25.Stephan, F.: Methods and theory of automata and languages. School of Computing, National University of Singapore (2016)Google Scholar
- 26.Wiehagen, R.: Limes-erkennung rekursiver funktionen durch spezielle strategien. J. Inf. Process. Cybern. (EIK) 12(1–2), 93–99 (1976)MathSciNetMATHGoogle Scholar
Copyright information
© Springer International Publishing AG, part of Springer Nature 2018