论文部分内容阅读
模拟进化计算是近年来信息科学、人工智能与计算机科学的“热点”研究领域,而由此派生的遗传算法是一族通过模拟自然进化过程搜索最优解的方法。其基本思想源于60年代,Holland在研究机器学习过程中,受达尔文进化论——适者生存的启发,而获得的一种概率搜索算法。该方法在早期作为一种自适应机器学习方法,而近几年在解全局优化问题、人工神经网络的训练与结构优化、程序设计自动化中的查错处理等方面已取得成功的应用,显示了非常广泛的应用前景。
Simulated evolutionary computation is a hot area of research in recent years in information science, artificial intelligence and computer science. The resulting genetic algorithm is a family of methods for searching for optimal solutions by simulating the natural evolutionary process. The basic idea was derived from the 1960s, Holland in the study of machine learning process, inspired by Darwin’s theory of survival of the fittest, and obtained a probabilistic search algorithm. In the early years, this method was used as an adaptive machine learning method. In recent years, this method has been successfully applied in solving global optimization problems, training and structural optimization of artificial neural networks, and error checking and processing in program design automation. A very wide range of applications.