Abstract
Subsymbolic approaches have been adopted in attempting to solve many AI problems. In order to find a near optimal solution to the problem a procedure is needed by which the subsymbolic components can be manipulated. In searching all but the simplest of solution spaces algorithms such as hill climbing will often result in only suboptimal solutions being found. Often search algorithms do not make sufficient use of information acquired from previous evaluations of possible solutions. Several forms of adaptive algorithm have been developed in an attempt to overcome this problem and produce robust search mechanisms, e.g., evolutionary algorithms, classifier systems. This paper discusses some adaptive algorithms and presents initial work on a novel form of adaptive algorithm.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Belaw, R.K., Booker, L.B.: (eds.) Proc. Fourth Int. Conf. Genetic Algorithms Morgan Kaufmann (1991).
Davis, T.E., Principe, J.C.: A Markov chain framework for the simple genetic algorithm. J. Evol. Comput. 1 (1993) 269–288.
Fogel, D.B.: System identification through simulated evolution: A machine learning approach to modeling. Ginn Press (1991).
Fogel, D.B.: Evolving artificial intelligence. PhD Thesis, University of California, San Diego, USA (1992).
Fogel, D.B.: Evolving behaviours in the iterated prisoner's dilemma. J. Evol. Comput. 1 (1993) 77–97.
Fogel, L.J., Owens, A.J., Walsh, M.J.: Artificial intelligence through simulated evolution. J. Wiley, New York (1966).
Forrest, S., Mitchell, M.: What makes a problem hard for a genetic algorithm? Some anomalous results and their explanation. Machine Learning 13 (1993) 285–319.
Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley (1989).
Grefenstette, J.J.: (ed.) Proc. First Int. Conf. Genetic Algorithms Lawrence Erlbaum Associates (1985).
Grefenstette, J.J.: (ed.) Proc. Second Int. Conf. on Genetic Algorithms lawrence Erlbaum Associates (1987).
Holland, J.H.: Adaption in natural and artificial systems. University of Mitchigan Press (1975).
Jones, T.: A model of landscapes. Santa Fe Institute, 1660 Old Pecos Trail, Suite A., Santa Fe, NM 87505, USA (1994).
Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing. Science 220 (1983) 671–680.
Lindsay, R.K.: Artificial evolution of intelligence. Contem. Psych. 13 (1968) 113–116.
Mason, A.J.: Crossover non-linearity ratios and the genetic algorithm: Escaping the blinkers of schema processing and intrinsic parallelism. Report No. 535b, School of Engineering, University of Auckland, Private Bag 92019, New Zealand (1993).
Nettleton, D.J., Garigliano, R.: Evolutionary algorithms and a fractal inverse problem. BioSystems (to appear).
Radcliffe, N.J.: Forma analysis and random respectful recombination. Proc. Fourth Int. Conf. on Genetic Algorithms Morgan Kaufman (1991).
Solomonoff, R.J.: Some recent work in artificial intelligence. Proc. IEEE 54 (1966) 1687–1697.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nettleton, D.J., Garigliano, R. (1995). Subsymbolic processing using adaptive algorithms. In: Calmet, J., Campbell, J.A. (eds) Integrating Symbolic Mathematical Computation and Artificial Intelligence. AISMC 1994. Lecture Notes in Computer Science, vol 958. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60156-2_17
Download citation
DOI: https://doi.org/10.1007/3-540-60156-2_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60156-2
Online ISBN: 978-3-540-49533-8
eBook Packages: Springer Book Archive