Abstract
We provide upper bounds for the Vapnik-Chervonenkis dimension of classes of subsets of that can be recognized by computer programs built from arithmetical assignments, infinitely differentiable algebraic operations (like k-root extraction and, more generally, operations defined by algebraic series of fractional powers), conditional statements and while instructions. This includes certain classes of GP-trees considered in Genetic Programming for symbolic regression and bi-classification. As a consequence we show explicit quantitative properties that can help to design the fitness function of a GP learning machine.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Aldaz, M., Heintz, J., Matera, G., Montaña, J.L., Pardo, L.M.: Time-space tradeoffs in algebraic complexity theory. Real computation and complexity (Schloss Dagstuhl, 1998). J. Complexity 16(1), 2–49 (2000)
Aldaz, M., Heintz, J., Matera, G., Montaña, J.L., Pardo, L.M.: Combinatorial hardness proofs for polynomial evaluation (extended abstract). In: Brim, L., Gruska, J., Zlatuška, J. (eds.) MFCS 1998. LNCS, vol. 1450, pp. 167–175. Springer, Heidelberg (1998)
Ben-Or, M.: Lower Bounds for Algebraic Computation Trees STOC 1983, pp. 80–86 (1981)
Blum, L., Cucker, F., Shub, M., Smale, S.: Complexity and real computation. Springer, New York (1998)
Blum, L., Shub, M., Smale, S.: On a theory of computation over the real numbers: NP completeness, recursive functions and universal machines [Bull. Amer. Math. Soc (N.S.) 21 (1989), no. 1, 1–46; MR0974426 (90a:68022)]. In: Workshop on Dynamical Systems (Trieste, 1988), pp. 23–52, Pitman Res. Notes Math. Ser. 221, Longman Sci. Tech., Harlow (1990)
Bochnak, J., Coste, M., Roy, M.-F.: Géométrie algébrique réelle (French) [Real algebraic geometry] Ergebnisse der Mathematik und ihrer Grenzgebiete (3) [Results in Mathematics and Related Areas (3)], vol. 12, pp. x+373. Springer-Verlag, Berlin (1987)
Cucker, F., Smale, S.: On the Mathematical foundations of learning. Bulletin (New Series) Of the AMS 39(1), 1–4 (2001)
Gelly, S., Teytaud, O., Bredeche, N., Schoenauer, M.: Universal Consistency and Bloat in GP. Revue d’Intelligence Artificielle 20(6), 805–827 (2006)
Goldberg, P., Jerrum, M.: Bounding the Vapnik-Chervonenkis dimension of concept classes parametrizes by real numbers. Machine Learning 18, 131–148 (1995)
Karpinski, M., Macintyre, A.: Bounding VC-dimension for neural networks: progress and prospects. In: Vitányi, P.M.B. (ed.) EuroCOLT 1995. LNCS, vol. 904, pp. 337–341. Springer, Heidelberg (1995)
Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge, MA, USA (1992)
Lugosi, G.: Pattern clasification and learning theory. In: Gyorfi, L. (ed.) Principles of nonparametric learning, pp. 5–62. Springer, Viena (2002)
Montaña, J.L., Pardo, L.M., Ramanakoraisina, R.: An extension of Warren’s lower bounds for approximations. J. Pure Appl. Algebra 87(3), 251–258 (1993)
Montaña, J.L., Pardo, L.M.: Lower bounds for arithmetic networks. Appl. Algebra Engrg. Comm. Comput. 4(1), 1–24 (1993)
Vapnik, V.: Statistical learning theory. John Willey & Sons, Chichester (1998)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Alonso, C.L., Montaña, J.L. (2007). Finiteness Properties of Some Families of GP-Trees. In: Borrajo, D., Castillo, L., Corchado, J.M. (eds) Current Topics in Artificial Intelligence. CAEPIA 2007. Lecture Notes in Computer Science(), vol 4788. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75271-4_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-75271-4_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75270-7
Online ISBN: 978-3-540-75271-4
eBook Packages: Computer ScienceComputer Science (R0)