作者: F. Boschetti , H. Takagi
关键词: Evolutionary computation 、 Machine learning 、 Artificial intelligence 、 Computer science 、 Data visualization 、 System testing 、 Visualization 、 Self-organizing map 、 Algorithm
摘要: We evaluate how visualization of an evolutionary computation (EC) landscape is effective using a geophysical task. This technique allows us to actively participate in EC optimization by viewing the distribution searching points on 2D space mapped from n-D landscape, and indicating where possible global optimum. construct Visualized GA system that includes self-organizing maps for compare its performance with normal simulation Sign tests comparisons show converges significantly faster than (p<0.01), which suggests further extensions enhance user interactivity.