A study on performance of MHDA in training MLPs. Issue 6 (8th July 2019)

• Record Type: Journal Article
• Authors: K.S., Sree Ranjini
• Is Part Of: Engineering computations. Volume 36:Issue 6(2019)
• Page Start: 1820
• Page End: 1834
• Publication Date: 2019-07-08
• Subjects: Classification -- Approximation -- Computational complexity -- MHDA -- MLPs; Computer-aided engineering -- Periodicals; Computer graphics -- Periodicals; 620.00285
• DOI: 10.1108/EC-05-2018-0216
• Languages: English
• ISSNs: 0264-4401

Abstract

Abstract : Purpose: In recent years, the application of metaheuristics in training neural network models has gained significance due to the drawbacks of deterministic algorithms. This paper aims to propose the use of a recently developed "memory based hybrid dragonfly algorithm" (MHDA) for training multi-layer perceptron (MLP) model by finding the optimal set of weight and biases. Design/methodology/approach: The efficiency of MHDA in training MLPs is evaluated by applying it to classification and approximation benchmark data sets. Performance comparison between MHDA and other training algorithms is carried out and the significance of results is proved by statistical methods. The computational complexity of MHDA trained MLP is estimated. Findings: Simulation result shows that MHDA can effectively find the near optimum set of weight and biases at a higher convergence rate when compared to other training algorithms. Originality/value: This paper presents MHDA as an alternative optimization algorithm for training MLP. MHDA can effectively optimize set of weight and biases and can be a potential trainer for MLPs.