Please use this identifier to cite or link to this item:
|Title:||Multi-criteria decision making based architecture selection for single-hidden layer feedforward neural networks||Author(s):||Wang, Philips Fu Lee
|Issue Date:||2019||Publisher:||Springer||Journal:||International Journal of Machine Learning and Cybernetics||Volume:||10||Issue:||4||Start page:||655||End page:||666||Abstract:||
Architecture selection is a fundamental problem in artificial neural networks, which could be treated as a decision making process that evaluates, ranks, and makes choices from a set of network structures. Traditional methods evaluate a network structure by designing a criterion based on a validation model or an error bound model. On one hand, the time complexity of a validation model is usually high; on the other hand, different validation models or error bound models may lead to different (even conflicting) results, which post challenges to the traditional single criterion-based architecture selection methods. In the area of decision making, many problems employed multiple criteria since the performance is better than using a single criterion. In this paper, we propose a multi-criteria decision making based architecture selection algorithm for single-hidden layer feedforward neural networks trained by extreme learning machine. Two criteria are incorporated into the selection process, i.e., training accuracy and the Q-value estimated by the localized generalization error model. The training accuracy reflects the capability of the model on correctly categorizing the known samples, and the Q-value estimated by localized generalization error model reflects the size of the neighbourhood of training samples in which the model can predict unseen samples with confidence. By achieving a trade-off between these two criteria, a new architecture selection algorithm is proposed. Experimental comparisons demonstrate the feasibility and effectiveness of the proposed method.
|URI:||https://repository.cihe.edu.hk/jspui/handle/cihe/832||DOI:||10.1007/s13042-017-0746-9||CIHE Affiliated Publication:||Yes|
|Appears in Collections:||CIS Publication|
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.