Abstract
We analyze iterative learning in the limit from positive data with the additional information provided by a counter. The simplest type of counter provides the current iteration number (counting up from 0 to infinity), which is known to improve learning power over plain iterative learning.
We introduce five other (weaker) counter types, for example only providing some unbounded and non-decreasing sequence of numbers. Analyzing these types allows for understanding what properties of a counter can benefit learning.
For the iterative setting, we completely characterize the relative power of the learning criteria corresponding to the counter types. In particular, for our types, the only properties improving learning power are unboundedness and strict monotonicity.
Furthermore, we show that each of our types of counter improves learning power over weaker ones in some settings, and that, for iterative learning criteria with one of these types of counter, separations of learning criteria are necessarily witnessed by classes containing only infinite languages.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baliga, G., Case, J., Merkle, W., Stephan, F., Wiehagen, W.: When unlearning helps. Information and Computation 206, 694–709 (2008)
Case, J.: Periodicity in generations of automata. Mathematical Systems Theory 8, 15–32 (1974)
Carlucci, L., Case, J., Jain, S., Stephan, F.: Results on memory-limited U-shaped learning. Information and Computation 205, 1551–1573 (2007)
Case, J., Jain, S., Lange, S., Zeugmann, T.: Incremental concept learning for bounded data mining. Information and Computation 152, 74–110 (1999)
Case, J., Kötzing, T.: Dynamic modeling in inductive inference. In: Freund, Y., Györfi, L., Turán, G., Zeugmann, T. (eds.) ALT 2008. LNCS (LNAI), vol. 5254, pp. 404–418. Springer, Heidelberg (2008)
Case, J., Kötzing, T.: Strongly non-U-shaped learning results by general techniques. In: Proceedings of COLT (Conference on Learning Theory), pp. 181–193 (2010)
Case, J., Kötzing, T.: Measuring learning complexity with criteria epitomizers. In: Proceedings of STACS (Symposion on Theoretical Aspects of Computer Science), pp. 320–331 (2011)
Case, J., Moelius, S.: Optimal language learning. In: Freund, Y., Györfi, L., Turán, G., Zeugmann, T. (eds.) ALT 2008. LNCS (LNAI), vol. 5254, pp. 419–433. Springer, Heidelberg (2008)
Case, J., Moelius, S.: U-shaped, iterative, and iterative-with-counter learning. Machine Learning 72, 63–88 (2008)
Freivalds, R., Kinber, E., Smith, C.: On the impact of forgetting on learning machines. Journal of the ACM 42, 1146–1168 (1995)
Gold, E.: Language identification in the limit. Information and Control 10, 447–474 (1967)
Jain, S., Osherson, D., Royer, J., Sharma, A.: Systems that Learn: An Introduction to Learning Theory, 2nd edn. MIT Press, Cambridge (1999)
Lange, S., Zeugmann, T.: Incremental learning from positive data. Journal of Computer and System Sciences 53, 88–103 (1996)
Royer, J., Case, J.: Subrecursive Programming Systems: Complexity and Succinctness. Research Monograph in Progress in Theoretical Computer Science. Birkhäuser, Boston (1994)
Rogers, H.: Theory of Recursive Functions and Effective Computability. McGraw Hill, New York (1987); Reprinted by MIT Press, Cambridge (1987)
Schäfer-Richter, G.: Über Eingabeabhängigkeit und Komplexität von Inferenzstrategien. PhD thesis, RWTH Aachen (1984)
Wexler, K., Culicover, P.: Formal Principles of Language Acquisition. MIT Press, Cambridge (1980)
Wiehagen, R.: Limes-Erkennung rekursiver Funktionen durch spezielle Strategien. Elektronische Informationverarbeitung und Kybernetik 12, 93–99 (1976)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kötzing, T. (2011). Iterative Learning from Positive Data and Counters. In: Kivinen, J., Szepesvári, C., Ukkonen, E., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2011. Lecture Notes in Computer Science(), vol 6925. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24412-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-24412-4_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24411-7
Online ISBN: 978-3-642-24412-4
eBook Packages: Computer ScienceComputer Science (R0)