Skip to main content
Springer Nature Link
Log in

Learning Automata

  • Reference work entry
  • First Online:
Encyclopedia of Algorithms

  • 333 Accesses

Footnote 1

Years and Authors of Summarized Original Work

  • 2000; Beimel, Bergadano, Bshouty, Kushilevitz, Varricchio

Problem Definition

This problem is concerned with the learnability of multiplicity automata in Angluin’s exact learning model and applications to the learnability of functions represented by small multiplicity automata.

The Learning Model

It is the exact learning model [2]: Let f be a target function. A learning algorithm may propose to an oracle, in each step, two kinds of queries: membership queries (MQ) and equivalence queries (EQ). In a MQ it may query for the value of the function f on a particular assignment z. The response to such a query is the value f(z). (If f is Boolean, this is the standard membership query.) In an EQ it may propose to the oracle a hypothesis function h. If h is equivalent to fon all input assignments, then the answer to the query is YES and the learning algorithm succeeds and halts. Otherwise, the answer to the equivalence query is NO and...

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    Stefano Varricchio: deceased

Recommended Reading

  1. Angluin D (1987) Learning regular sets from queries and counterexamples. Inf Comput 75:87–106

    Article  MathSciNet  MATH  Google Scholar 

  2. Angluin D (1988) Queries and concept learning. Mach Learn 2(4):319–342

    Google Scholar 

  3. Beimel A, Bergadano F, Bshouty NH, Kushilevitz E, Varricchio S (1996) On the applications of multiplicity automata in learning. In: Proceedings of the 37th annual IEEE symposium on foundations of computer science, Burlington, Vermont, USA. IEEE Computer Society, Los Alamitos, pp 349–358

    Google Scholar 

  4. Beimel A, Bergadano F, Bshouty NH, Kushilevitz E, Varricchio S (2000) Learning functions represented as multiplicity automata. J ACM 47:506–530

    Article  MathSciNet  MATH  Google Scholar 

  5. Beimel A, Kushilevitz E (1997) Learning boxes in high dimension. In: Ben-David S (ed) 3rd European conference on computational learning theory (EuroCOLT ’97), Jerusalem, Israel. Lecture notes in artificial intelligence, vol 1208. Springer, Berlin, pp 3–15. Journal version: Algorithmica 22:76–90 (1998)

    MathSciNet  Google Scholar 

  6. Bergadano F, Catalano D, Varricchio S (1996) Learning sat-k-DNF formulas from membership queries. In: Proceedings of the 28th annual ACM symposium on the theory of computing, Philadelphia, Pennsylvania, USA. ACM, New York, pp 126–130

    Google Scholar 

  7. Bergadano F, Varricchio S (1994) Learning behaviors of automata from multiplicity and equivalence queries. In: Proceedings of 2nd Italian conference on algorithms and complexity, Rome, Italy. Lecture notes in computer science, vol 778. Springer, Berlin, pp 54–62. Journal version: SIAM J Comput 25(6):1268–1280 (1996)

    Google Scholar 

  8. Bergadano F, Varricchio S (1996) Learning behaviors of automata from shortest counterexamples. In: EuroCOLT ’95, Barcelona, Spain. Lecture notes in artificial intelligence, vol 904. Springer, Berlin, pp 380–391

    Google Scholar 

  9. Bisht L, Bshouty NH, Mazzawi H (2006) On optimal learning algorithms for multiplicity automata. In: Proceedings of 19th annual ACM conference on computational learning theory, Pittsburgh, Pennsylvania, USA. Lecture notes in computer science, vol 4005. Springer, Berlin, pp 184–198

    Google Scholar 

  10. Blum A, Khardon R, Kushilevitz E, Pitt L, Roth D (1994) On learning read-k-satisfy-j DNF. In: Proceedings of the 7th annual ACM conference on computational learning theory, New Brunswick, New Jersey, USA. ACM, New York, pp 110–117

    Google Scholar 

  11. Bshouty NH (1993) Exact learning via the monotone theory. In: Proceedings of the 34th annual IEEE symposium on foundations of computer science, Palo Alto, California, USA. IEEE Computer Society, Los Alamitos, pp 302–311. Journal version: Inf Comput 123(1):146–153 (1995)

    Google Scholar 

  12. Bshouty NH (1995) Simple learning algorithms using divide and conquer. In: Proceedings of 8th annual ACM conference on computational learning theory, Santa Cruz, California, USA. ACM, New York, pp 447–453. Journal version: Comput Complex 6:174–194 (1997)

    Google Scholar 

  13. Bshouty NH, Tamon C, Wilson DK (1998) Learning matrix functions over rings. Algorithmica 22(1/2):91–111

    Article  MathSciNet  MATH  Google Scholar 

  14. Kushilevitz E (1996) A simple algorithm for learning \(O(\log n)\)-term DNF. In: Proceedings of 9th annual ACM conference on computational learning theory, Desenzano del Garda, Italy. ACM, New York, pp 266–269. Journal version: Inf Process Lett 61(6):289–292 (1997)

    Google Scholar 

  15. Kushilevitz E, Mansour Y (1993) Learning decision trees using the fourier spectrum. SIAM J Comput 22(6):1331–1348

    Article  MathSciNet  MATH  Google Scholar 

  16. Melideo G, Varricchio S (1998) Learning unary output two-tape automata from multiplicity and equivalence queries. In: ALT ’98, Otzenhausen, Germany. Lecture notes in computer science, vol 1501. Springer, Berlin, pp 87–102

    Google Scholar 

  17. Ohnishi H, Seki H, Kasami T (1994) A polynomial time learning algorithm for recognizable series. IEICE Trans Inf Syst E77-D(10)(5):1077–1085

    Google Scholar 

  18. Schapire RE, Sellie LM (1996) Learning sparse multivariate polynomials over a field with queries and counterexamples. J Comput Syst Sci 52(2):201–213

    Article  MathSciNet  MATH  Google Scholar 

  19. Valiant LG (1984) A theory of the learnable. Commun ACM 27(11):1134–1142

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Roma, Rome, Italy

    Stefano Varricchio

Authors
  1. Stefano Varricchio
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL, USA

    Ming-Yang Kao

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer Science+Business Media New York

About this entry

Cite this entry

Varricchio, S. (2016). Learning Automata. In: Kao, MY. (eds) Encyclopedia of Algorithms. Springer, New York, NY. https://doi.org/10.1007/978-1-4939-2864-4_194

Download citation

Publish with us

Policies and ethics