Adaptive polyclonal programming algorithm with applications

Abstract

Based on the clonal selection theory, the main mechanism of immune clone applied in artificial intelligence is analyzed in this paper. A new operator, adaptive polyclonal operator as well as a novel artificial immune system algorithm, APPA (adaptive polyclonal programming algorithm), is put forward. Compared with some other evolutionary programming algorithms (like breeder genetic algorithm), APPA, behaving as an evolutionary strategy, is shown to be capable of solving complex machine learning tasks effectively, like multimodal function optimization.