Self-Organizing and Error Driven (SOED) artificial neural network for smarter classifications. Issue 4 (19th April 2017)

• Record Type: Journal Article
• Authors: Jafari-Marandi, Ruholla; Khanzadeh, Mojtaba; Smith, Brian K.; Bian, Linkan
• Is Part Of: Journal of computational design and engineering. Volume 4:Issue 4(2017)
• Page Start: 282
• Page End: 304
• Publication Date: 2017-04-19
• Subjects: Classification -- Artificial Neural Network (ANN) -- Self-Organizing Map (SOM); Engineering -- Data processing -- Periodicals; Computer-aided design -- Periodicals; Computer-aided design; Engineering -- Data processing; Electronic journals; Electronic journals; Periodicals; 620.0042
• DOI: 10.1016/j.jcde.2017.04.003
• Languages: English
• ISSNs: 2288-4300

Abstract

Graphical abstract: Abstract: Classification tasks are an integral part of science, industry, business, and health care systems; being such a pervasive technique, its smallest improvement is valuable. Artificial Neural Network (ANN) is one of the strongest techniques used in many disciplines for classification. The ANN technique suffers from drawbacks such as intransparency in spite of its high prediction power. In this paper, motivated by learning styles in human brains, ANN's shortcomings are assuaged and its prediction power is improved. Self-Organizing Map (SOM), an ANN variation which has strong unsupervised power, and Feedforward ANN, traditionally used for classification tasks, are hybridized to solidify their benefits and help remove their limitations. The proposed method, which we name Self-Organizing Error-Driven (SOED) Artificial Neural Network, shows significant improvements in comparison with usual ANNs. We show SOED is a more accurate, more reliable, and more transparent technique through experimentation with five different datasets.