Learning of RBF network by using Teaching-Learning Based Optimization (TLBO) Algorithm

Abstract

TLBO (Teaching -learning -based optimization) is a nature inspired optimization algorithm. There are many evolutionary algorithms like genetic algorithm, ant colony optimization, particle swarm optimization etc. All these algorithms depend on algorithmic parameters. A small change in these algorithmic parameters may cause a large change in the effectiveness of the algorithm. In this scenario TLBO is coming to picture. TLBO is independent of algorithmic parameters. TLBO follows the Teacher -Student and Student -Student interaction in the class room. TLBO have two phases, Teacher Phase and Learner Phase. The key feature of TLBO is, in the first stage algorithm attains average learning, in the second stage algorithm pick the best solution. In teacher phase, teacher is one of the learners among the population who has best knowledge level. Teacher tries to improve the mean knowledge level of class up to his level. When learners reached teacher's knowledge level, algorithm needs a new teacher with more knowledge. In the learner phase, learners interact with each other to improve their knowledge. This technique will be used in the learning of the parameters of the RBF network

TLBO with variable weights applied to shop scheduling problems

“…As mentioned earlier, TLBO is a population‐based algorithm that simulates the dynamics of teaching–learning processes. TLBO has been successfully used in a wide range of optimisation problems [6–10], with an additional advantage of a reduced number of parameters [11].…”