Abstract Interpolation, compression, or even use of a large data set is enhanced if the data set can be partitioned into sub- sets with a more uniform internal character. This paper presents a technique for more rapid automatic segregation of data sets with an evolutionary algorithm. We improve performance of our evolutionary algorithm by imposing a graphical geography that, we conjecture, slows the spread of information within the evolving population and so retards premature convergence. We present results on a trial data segregation problem for 23 dieren t graphical geographies. Change of geography has a statistically signican t impact on performance.
分享
引用
