Learning and optimization using the clonal selection principle

 The clonal selection principle is used to explain the basic features of an adaptive immune response to an antigenic stimulus. It establishes the idea that only those cells that recognize the antigens are selected to proliferate. The selected cells are subject to an affinity maturation process, which improves their affinity to the selective antigens. In this paper, we propose a computational implementation of the clonal selection principle that explicitly takes into account the affinity maturation of the immune response. The general algorithm, named CLONALG, is primarily derived to perform machine-learning and pattern recognition tasks, and then it is adapted to solve optimization problems, emphasizing multimodal and combinatorial optimization. Two versions of the algorithm are derived, their computational cost per iteration is presented and a sensitivity analysis with relation to the userdefined parameters is given. CLONALG is also contrasted with evolution strategies and genetic algorithms. Several benchmark problems are considered to evaluate the performance of CLONALG and it is also compared to a niching method for multimodal function optimization. Index Terms  Artificial immune systems, clonal selection principle, evolutionary algorithms, optimization, pattern recognition.