学术报告

报告题目：Among-site Rate Variation: Adaptation of Genetic Algorithm Mutation Rates at each Single Site

报告人：美国伊利诺伊大学芝加哥分校Peter C. Nelson教授

报告时间：6月19日（周四）下午2:30-4:00

报告地点：科学馆101报告厅

Peter Nelson is the Dean of Engineering at the University of Illinois at Chicago. He is also a Professor in the Department of Computer Science.

报告内容简介：This talk is concerned with proposing an elitist genetic algorithmwhich makes use of a new mutation scheme aimed to tackle bothexplorative and exploitative responsibilities of genetic operators.The proposed mutation scheme follows an approach similar to motifrepresentation in biology, to derive the underlying pattern ofhighly-fit solutions discovered so far. This pattern is then usedto derive mutation rates specified for every site along the encodedsolutions. The site-specific rates are amended for every individualto balance the required explorative and exploitative power. Todemonstrate the efficacy of the proposed algorithm, the method isevaluated using a set of benchmark problems and compared with aseries of relevant evolutionary algorithms. The results demonstratethat the suggested method significantly outperforms the comparedevolutionary algorithms. The Markov chain model of the proposedmethod is also derived and used to analyze its convergence properties.