ABSTRACT
In computational intelligence, the term 'memetic algorithm' has come to be associated with the algorithmic pairing of a global search method with a local search method. In a sociological context, a 'meme' has been loosely defined as a unit of cultural information, the social analog of genes for individuals. Both of these definitions are inadequate, as 'memetic algorithm' is too specific, and ultimately a misnomer, as much as a 'meme' is defined too generally to be of scientific use. In this paper, we extend the notion of memes from a computational viewpoint and explore the purpose, definitions, design guidelines and architecture for effective memetic computing. Utilizing two genetic programming test-beds (the even-parity problem and the Pac-Man video game), we demonstrate the power of high-order meme-based learning, known as meta-learning. With applications ranging from cognitive science to machine learning, meta-learning has the potential to provide much-needed stimulation to the field of computational intelligence by providing a framework for higher order learning.
- D. Shahaf and E. Amir, "Towards a Theory of AI Completeness," 8th Interational Symposium on Logic Formalizations of Commonsense Reasoning, 2007.Google Scholar
- D. Lenat and R. V. Guha, Building Large Knowledge-Based Systems: Addison-Wesley, 1989. Google ScholarDigital Library
- J. R. Koza, "Hierarchical genetic algorithms operating on populations of computer programs," in International Joint Conference on Artificial Intelligence, 1989, pp. 768--774. Google ScholarDigital Library
- D. Dennett, Darwin's Dangerous Idea. New York: Touchstone Press, 2005.Google Scholar
- Y. S. Ong and A. J. Keane, "Meta-Lamarckian learning in memetic algorithms," IEEE Transactions on Evolutionary Computation, vol. 8, pp. 99--110, 2004. Google ScholarDigital Library
- P. Moscato, "On evolution, search, optimization, genetic algorithms and martial arts: Towards memetic algorithms," Caltech Concurrent Computation Program, C3P Report, 826. 1989.Google Scholar
- R. J. Meuth, M.-H. Lim, Y.-S. Ong, and D. C. Wunsch, "A Proposition on Memes and Meta-Memes in Computing for Higher-Order Learning," Journal of Memetic Computing, vol. 1, 2009.Google Scholar
- J. R. Koza, "Hierarchical Automatic Function Definition in Genetic Programming," in Foundations of Genetic Algorithms 2: Morgan Kaufmann, 1992, pp. 297--318.Google Scholar
- J. R. Koza, "Evolution and co-evolution of computer programs to control independent-acting agents," in From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior, 1991. Google ScholarDigital Library
Index Terms
- Meta-learning genetic programming
Recommendations
PAC learning and genetic programming
GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computationGenetic programming (GP) is a very successful type of learning algorithm that is hard to understand from a theoretical point of view. With this paper we contribute to the computational complexity analysis of genetic programming that has been started ...
Online meta-learning by parallel algorithm competition
GECCO '18: Proceedings of the Genetic and Evolutionary Computation ConferenceThe efficiency of reinforcement learning algorithms depends critically on a few meta-parameters that modulate the learning updates and the trade-off between exploration and exploitation. The adaptation of the meta-parameters is an open question, which ...
Neural network crossover in genetic algorithms using genetic programming
AbstractThe use of genetic algorithms (GAs) to evolve neural network (NN) weights has risen in popularity in recent years, particularly when used together with gradient descent as a mutation operator. However, crossover operators are often omitted from ...
Comments