Búsqueda de la estructura óptima de redes neurales con Algoritmos Genéticos y Simulated Annealing. Verificación con el benchmark PROBEN1

IF 3.4 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2007-06-01 DOI:10.4114/IA.V11I34.908

Francisco Yepes Barrera

引用次数: 4

Abstract

Este articulo describe el uso de algoritmos geneticos (AG) y simulated annealing (SA) en la busqueda de configuraciones optimas de redes neurales artificiales, dentro de una arquitectura software, TSAGANN. El estudio comparativo ha sido realizado con benchmarks consolidados y es ilustrado en detalle. El analisis estadistico de los resultados indica que SA es tan eficiente como AG para este tipo de problemas, permitiendo incluso realizar exploraciones en el espacio del problema con un menor numero de evaluaciones de las usadas por el AG para obtener resultados comparables.

查看原文本刊更多论文

利用遗传算法和模拟退火寻找神经网络的最优结构。使用PROBEN1基准测试进行验证

本文描述了在TSAGANN软件架构中使用遗传算法(AG)和模拟退火算法(SA)来搜索人工神经网络的最佳配置。比较研究是根据综合基准进行的，并详细说明。结果的统计分析表明，SA在这类问题上与AG一样有效，甚至允许在问题空间中进行探索，与AG用于获得可比结果的评估数量相比，允许更少的评估。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-

CiteScore

2.00

自引率

0.00%

发文量

审稿时长

8 weeks

期刊介绍： Inteligencia Artificial is a quarterly journal promoted and sponsored by the Spanish Association for Artificial Intelligence. The journal publishes high-quality original research papers reporting theoretical or applied advances in all branches of Artificial Intelligence. The journal publishes high-quality original research papers reporting theoretical or applied advances in all branches of Artificial Intelligence. Particularly, the Journal welcomes: New approaches, techniques or methods to solve AI problems, which should include demonstrations of effectiveness oor improvement over existing methods. These demonstrations must be reproducible. Integration of different technologies or approaches to solve wide problems or belonging different areas. AI applications, which should describe in detail the problem or the scenario and the proposed solution, emphasizing its novelty and present a evaluation of the AI techniques that are applied. In addition to rapid publication and dissemination of unsolicited contributions, the journal is also committed to producing monographs, surveys or special issues on topics, methods or techniques of special relevance to the AI community. Inteligencia Artificial welcomes submissions written in English, Spaninsh or Portuguese. But at least, a title, summary and keywords in english should be included in each contribution.