Abstract
Universal induction is a crucial issue in AGI. Its practical applicability can be achieved by the choice of the reference machine or representation of algorithms agreed with the environment. This machine should be updatable for solving subsequent tasks more efficiently. We study this problem on an example of combinatory logic as the very simple Turing-complete reference machine, which enables modifying program representations by introducing different sets of primitive combinators. Genetic programming system is used to search for combinator expressions, which are easily decomposed into sub-expressions being recombined in crossover. Our experiments show that low-complexity induction or prediction tasks can be solved by the developed system (much more efficiently than using brute force); useful combinators can be revealed and included into the representation simplifying more difficult tasks. However, optimal sets of combinators depend on the specific task, so the reference machine should be adaptively chosen in coordination with the search engine.
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
Solomonoff, R.: Algorithmic Probability, Heuristic Programming and AGI. In: Baum, E., Hutter, M., Kitzelmann, E. (eds.) Proc. 3rd Conf. on Artificial General Intelligence. Advances in Intelligent Systems Research, vol. 10, pp. 151–157 (2010)
Potapov, A., Rodionov, S., Myasnikov, A., Galymzhan, B.: Cognitive Bias for Universal Algorithmic Intelligence. SarXiv:1209.4290v1 [cs.AI] (2012)
Skaba, W.: Binary Space Partitioning as Intrinsic Reward. In: Bach, J., Goertzel, B., Iklé, M. (eds.) AGI 2012. LNCS, vol. 7716, pp. 282–291. Springer, Heidelberg (2012)
Looks, M., Goertzel, B.: Program Representation for General Intelligence. In: Goertzel, B., Hitzler, P., Hutter, M. (eds.) Proc. 2nd Conf. on AGI, Arlington, Virginia, USA, March 6-9. Advances in Intelligent Systems Research, vol. 8, pp. 114–119 (2009)
Friedlander, D., Franklin, S.: LIDA and a Theory of Mind. In: Proc. 1st AGI Conference. Frontiers in Artificial Intelligence and Applications, vol. 171, pp. 137–148 (2008)
Pankov, S.: A Computational Approximation to the AIXI Model. In: Proc. 1st AGI Conference. Frontiers in Artificial Intelligence and Applications, vol. 171, pp. 256–267 (2008)
Tromp, J.: Binary Lambda Calculus and Combinatory Logic. In: Kolmogorov Complexity and Applications (2006), A Revised Version is available at http://homepages.cwi.nl/tromp/cl/LC.pdf
Fuchs, M.: Large Populations are not always the best choice in Genetic Programming. In: Proc. of the Genetic and Evolutionary Computation Conference, GECCO 1999 (1999)
Briggs, F., O’Neill, M.: Functional Genetic Programming with Combinators. In: Proc. of the Third Asian-Pacific Workshop on Genetic Programming, pp. 110–127 (2006)
Solomonoff, R.: Progress in Incremental Machine Learning. Technical Report IDSIA-16-03, IDSIA (2003)
Schmidhuber, J.: The New AI: General & Sound & Relevant for Physics. In: Goertzel, B., Pennachin, C. (eds.) Artificial General Intelligence. Cognitive Technologies, pp. 175–198. Springer (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Potapov, A., Rodionov, S. (2013). Universal Induction with Varying Sets of Combinators. In: Kühnberger, KU., Rudolph, S., Wang, P. (eds) Artificial General Intelligence. AGI 2013. Lecture Notes in Computer Science(), vol 7999. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39521-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-39521-5_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39520-8
Online ISBN: 978-3-642-39521-5
eBook Packages: Computer ScienceComputer Science (R0)