Conference Paper

A Strategy of Mutation History Learning in Immune Clonal Selection Algorithm.

DOI: 10.1007/11903697_10 Conference: Simulated Evolution and Learning, 6th International Conference, SEAL 2006, Hefei, China, October 15-18, 2006, Proceedings
Source: DBLP

ABSTRACT A novel strategy termed as mutation history learning strategy (MHLS) is proposed in this paper. In MHLS, a vector called mutation
memory is introduced for each antibody and a new type of mutation operation based on mutation memory is also designed. The
vector of mutation memory is learned from a certain antibody’s iteration history and used as guidance for its further evolution.
The learning and usage of history information, which is absent from immune clonal selection algorithm (CSA), is shown to be
an efficient measure to guide the direction of the evolution and accelerate algorithm’s converging speed. Experimental results
show that MHLS improves the performance of CSA greatly in dealing with the function optimization problems.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Inspired by Darwin's theory of natural selection to explain the diversity and adaptability of life, Burnet's clonal selection theory explains the diversity and learning properties of the acquired immune system of vertebrates. In a similar mirroring manner to the field of evolutionary computation that attempts to use the principles of the Darwinian theory and genetics to address practical engineering problems, a new field of study called 'Clonal Selection Algorithms' has emerged that attempts the same task by abstracting and applying the principles of Burnet's foundational immunological theory. This paper provides a summary of this new field of clonal selection algorithms and proposes an algorithm taxonomy, a standardized nomenclature, and a general model of such algorithms. Finally, the field is compared and contrasted to the field of evolutionary computation, and general research trends are discussed. Artificial Immune Systems (AIS) is the investigation of models and abstractions of the vertebrate (typically mammalian) immune system and the application of these models and algorithms to practical endeavours such computation problem domains in the fields of science, engineering, and information technology (88). Although the source of inspiration for computational models in the immune system is near limitless, four main sub fields of research have emerged in AIS cantered on prominent immunological theories; negative selection algorithms (NSA), immune network algorithms (INA), danger theory algorithms (DTA), and clonal selection algorithms (CSA).