Teaching-learning-based Optimization (TLBO) is a popular meta-heuristic optimisation method that has been used in solving a number of scientific and engineering problems. In this paper, a new variant, namely Teaching-learning-feedback-based Optimization (TLFBO) is proposed. In addition to the two phases in the canonical TLBO, an additional feedback learning phase is employed to further speed up the convergence. The teacher in the previous generation is recorded and communicates with the current teacher to provide combined feedbacks to the learners and supervise the learning direction to avoid wasting computational efforts incurred in the previous generations. Numerical experiments on 10 well-known benchmark functions are conducted to evaluate the performance of the TLFBO, and experimental results show that the proposed TLFBO has a superior and competitive capability in solving continuous optimisation problems.
KeywordsTeaching-learning-based Optimization (TLBO) Feedback Global optimization Heuristic method
This paper was partially funded by the EPSRC under grant EP/P004636/1 and partially supported by NSFC under 61673256, and Shanghai Science Technology Commission under grant No. 14ZR1414800.
- 6.Holland, J.H.: Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence. MIT Press, Cambridge (1992)Google Scholar
- 7.Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of the IEEE International Conference on Neural Networks, vol. 4, pp. 1942–1948, November 1995Google Scholar
- 10.Rao, R., Patel, V.: Comparative performance of an elitist teaching-learning-based optimization algorithm for solving unconstrained optimization problems. Int. J. Ind. Eng. Comput. 4(1), 29–50 (2013)Google Scholar
- 16.Yang, Z., Li, K., Foley, A., Zhang, C.: A new self-learning TLBO algorithm for RBF neural modelling of batteries in electric vehicles. In: 2014 IEEE Congress on Evolutionary Computation (CEC), pp. 2685–2691 (2014)Google Scholar