Training feedforward neural networks using multi-verse optimizer for binary classification problems

被引：163

作者：

Faris, Hossam ^{[1
]}

Aljarah, Ibrahim ^{[1
]}

Mirjalili, Seyedali ^{[2
]}

机构：

[1] Univ Jordan, King Abdullah II Sch Informat Technol, Business Informat Technol Dept, Amman, Jordan

[2] Griffith Univ, Sch Informat & Commun Technol, Brisbane, Qld 4111, Australia

来源：

APPLIED INTELLIGENCE | 2016年 / 45卷 / 02期

关键词：

Multi-verse optimizer; MVO; Multilayer perceptron; MLP; Training neural network; Evolutionary algorithm; GENETIC ALGORITHM;

D O I：

10.1007/s10489-016-0767-1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper employs the recently proposed nature-inspired algorithm called Multi-Verse Optimizer (MVO) for training the Multi-layer Perceptron (MLP) neural network. The new training approach is benchmarked and evaluated using nine different bio-medical datasets selected from the UCI machine learning repository. The results are compared to five classical and recent evolutionary metaheuristic algorithms: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution (DE), FireFly (FF) Algorithm and Cuckoo Search (CS). In addition, the results are compared with two well-regarded conventional gradient-based training methods: the conventional Back-Propagation (BP) and the Levenberg-Marquardt (LM) algorithms. The comparative study demonstrates that MVO is very competitive and outperforms other training algorithms in the majority of datasets in terms of improved local optima avoidance and convergence speed.

引用

页码：322 / 332

页数：11

共 35 条

[11] Artificial neural networks: fundamentals, computing, design, and application [J].

Basheer, IA ;

Hajmeer, M .

JOURNAL OF MICROBIOLOGICAL METHODS, 2000, 43 (01) :3-31

[12]

Czerniak J, 2003, SPRINGER INT SER ENG, V752, P41

[13]

Fausett L.V., 1994, Fundamentals of Neural Networks: Architectures, Algorithms and Applications

[14] Comparing backpropagation with a genetic algorithm for neural network training [J].

Gupta, JND ;

Sexton, RS .

OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE, 1999, 27 (06) :679-684

[15]

Holland I.H., 1975, ADAPTATION NATURAL A

[16]

LICHMAN M., 2013, UCI MACHINE LEARNING

[17] Exploiting Nonlinear recurrence and Fractal scaling properties for voice disorder detection [J].

Little, Max A. ;

McSharry, Patrick E. ;

Roberts, Stephen J. ;

Costello, Declan A. E. ;

Moroz, Irene M. .

BIOMEDICAL ENGINEERING ONLINE, 2007, 6 (1)

[18] Evolving neural network using real coded genetic algorithm (GA) for multispectral image classification [J].

Liu, ZJ ;

Liu, AX ;

Wang, CY ;

Niu, Z .

FUTURE GENERATION COMPUTER SYSTEMS, 2004, 20 (07) :1119-1129

[19] Particle swarms for feedforward neural network training [J].

Mendes, R ;

Cortez, P ;

Rocha, M ;

Neves, J .

PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, :1895-1899

[20] Multi-Verse Optimizer: a nature-inspired algorithm for global optimization [J].

Mirjalili, Seyedali ;

Mirjalili, Seyed Mohammad ;

Hatamlou, Abdolreza .

NEURAL COMPUTING & APPLICATIONS, 2016, 27 (02) :495-513

← 1 2 3 4 →