ALENA. Adaptive-Length Evolving Neural Arrays

• Autores: Leonardo César Corbalán, Laura Cristina Lanzarini , Armando De Giusti
• Localización: Journal of Computer Science and Technology, ISSN-e 1666-6038, Vol. 4, Nº. 1, 2004 (Ejemplar dedicado a: Tenth Issue), págs. 59-65
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Evolving neural arrays (ENA) have proved to be capable of learning complex behaviors, i.e., problems whose solution requires strategy learning. For this reason, they present many applications in various areas such as robotics and process control. Unlike conventional methods "based on a single neural network" ENAs are made up of a set of networks organized as an array. Each of them represents a part of the expected solution. This work describes a new method, ALENA, that enhances the solutions obtained by solving the main deficiencies of ENA since it eases the obtaining of specialized components, does not require the explicit decomposition of the problem into subtasks, and is capable of automatically adjusting the arrays length for each particular use. The measurements of the proposed method "applied to problems of obstacle evasion and objects collection" show the superiority of ALENA in relation to the traditional methods that deal with populations of neural networks. SANE has been used in particular as a comparative referent due to its high performance. Eventually, conclusions and some future lines of work are presented.

• Referencias bibliográficas
  • References [1] Bruce, J. and Miikkulainnen, R. Evolving Populations Of Expert Neural Networks. Department of Computer Sciences, The University...
  • [2] Corbalán, L., Pisano, M., Osella Massa, G. y Lanzarini L. Criaturas Virtuales especificadas a través de Redes Neuronales Evolutivas. VII...
  • [3] Corbalán Leonardo. Evolución de redes neuronales para comandar criaturas que alcanzan objetivos sorteando obstáculos en un entorno virtual...
  • [4] Corbalán Leonardo y Lanzarini Laura. Arreglos neuronales evolutivos aplicados a la evasión de obstáculos y alcance de objetivos. VIII...
  • [5] Corbalán Leonardo y Lanzarini Laura. An ENA-Based Strategy Replacing Subobjectives Definition in Incremental Learning. International Conference...
  • [6] Freeman, J. A. & Skapura, D. M. Redes neuronales Algoritmos, aplicaciones y técnicas de programación. Addison–Wesley, 1991. Versión...
  • [7] Goldberg, D. E. Genetic Algorithms in Search, Optimization, and Machine Learning. Addison–Wesley, 1989. pág. 10
  • [8] Gomez, F. and Miikkulainen, R. Incremental Evolution Of Complex General Behavior Department of Computer Sciences, The University of Texas...
  • [9] Moriarty, D. E. & Miikkulainen, R. Efficient Reinforcement Learning through Symbiotic Evolution. Department of Computer Sciences,...
  • [10] Moriarty, D. E. Symbiotic Evolution of Neural Networks in Sequential Decision Tasks. Department of Computer Sciences, The University...
  • [11] Moriarty, D. E. & Miikkulainen, R. Forming Neural Networks Through Efficient and Adaptive Coevolution. Information Sciences Institute,...
  • [12] Yao, X. and Liu, Y. Ensemble Structure of Evolutionary Artificial Neural networks. Computational intelligence Group, School of Computer...
  • [13] Yao, X. and Liu, Y. A New Evolutionary System for Evolving Artificial Neural Networks. IEEE Transactions on Neural Networks, Vol 8, nro....
  • [14] Yao, X. Evolving Artificial Neural networks. School of Computer Science The University of Birmingham Edgbaston, Birmingham B15 2TT. Proceedings...