Multitasking Genetic Algorithm (MTGA) for Fuzzy System Optimization

Abstract

Multi-task learning uses auxiliary data or knowledge from relevant tasks to facilitate the learning in a new task. Multitask optimization applies multi-task learning to optimization to study how to effectively and efficiently tackle multiple optimization problems simultaneously. Evolutionary multi-tasking, or multi-factorial optimization, is an emerging subfield of multitask optimization, which integrates evolutionary computation and multi-task learning. This paper proposes a novel and easy-toimplement multi-tasking genetic algorithm (MTGA), which copes well with significantly different optimization tasks by estimating and using the bias among them. Comparative studies with eight state-of-the-art single-and multi-task approaches in the literature on nine benchmarks demonstrated that on average the MTGA outperformed all of them, and had lower computational cost than six of them. Based on the MTGA, a simultaneous optimization strategy for fuzzy system design is also proposed. Experiments on simultaneous optimization of type-1 and interval type-2 fuzzy logic controllers for couple-tank water level control demonstrated that the MTGA can find better fuzzy logic controllers than other approaches.

Evolutionary Multitask Optimization: a Methodological Overview, Challenges and Future Research Directions

“…Example of this specific trend is the well-known assortative mating, which can be materialized through i) a common crossover operation as in MFEA, MFEA-II and many other MFO techniques [18,31,27]; ii) based on mutation strategies as in DE inspired techniques [98,72,73]; or iii) the velocity based movements of PSO inspired methods [69,75,97]. Another commonly used mechanism for conducting intra-task knowledge transfer is the one used by MM methods, in which multiple populations coexists, each one devoted to the resolution of one specific task [25,105,107,114,26]. In that cases, the knowledge sharing is conducted mainly by migrating solutions among subpopulations, modifying in this way the optimizing task of individuals.…”

“…The same trend is also adopted in [106], in which a MM method named as Differential Evolutionary Multitask Optimization is proposed, in which the knowledge sharing is conducted through the migration of individuals among populations. A similar philosophy is followed in the Multitasking Genetic Algorithm modeled in [107], in which a population of solutions is created for each optimizing problem, and the knowledge sharing is realized at each iteration through the transference of different chromosomes among populations.…”

Deep Neural Fuzzy System Oriented toward High-Dimensional Data and Interpretable Artificial Intelligence

“…In recent years, great efforts have been made to improve FSs [8]. Evolutionary algorithms (EAs) [9,10], the gradient descent (GD) algorithm [11], and GD plus least squares estimation (LSE) [12] have been proposed to optimize FSs. Although EAs can search for the optimal solution with enough iterations, the computational cost is too expensive to be suitable for the optimization of FSs.…”

Supervised Enhanced Soft Subspace Clustering (SESSC) for TSK Fuzzy Classifiers

“…Many data-driven algorithms have been proposed to tune TSK fuzzy systems [6]- [13]. Optimizing a TSK fuzzy system involves fine-tuning both the antecedent parameters and the consequent parameters, which can be done separately or simultaneously [7], [8], [10]- [17]. When they are optimized separately, the consequent parameters are usually obtained by least squares estimation (LSE), e.g., in an adaptive neuro fuzzy inference system (ANFIS) [10].…”