Describing Quantum-Inspired Linear Genetic Programming from symbolic regression problems
Douglas Mota Dias, Marco Aurélio C. Pacheco · 2012
Quantum-inspired evolutionary algorithms (QIEAs) exploit principles of quantum mechanics to improve the performance of classical evolutionary algorithms. This paper describes the latest version of a QIEA model (“Quantum-Inspired Linear Genetic Programming” - QILGP) to evolve machine code programs. QILGP is inspired on multilevel quantum systems and its operation is based on quantum individuals, which represent a superposition of all programs of search space (solutions). Symbolic regression problems and the current more efficient model to evolve machine code (AIMGP) are used in comparative tests, which aim to evaluate the performance impact of introducing demes (subpopulations) and a limited migration strategy in this version of QILGP. It outperforms AIMGP by obtaining better solutions with fewer parameters and operators. The performance improvement achieved by this latest version of QILGP encourages its ongoing and future enhancements. Thus, this paper concludes that the quantum inspiration paradigm can be a competitive approach to evolve programs more efficiently.