Towards improving the convolutional neural networks for deep learning using the distributed artificial bee colony method
- PDF / 1,564,605 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 44 Downloads / 218 Views
ORIGINAL ARTICLE
Towards improving the convolutional neural networks for deep learning using the distributed artificial bee colony method Anan Banharnsakun1 Received: 19 August 2017 / Accepted: 17 March 2018 © Springer-Verlag GmbH Germany, part of Springer Nature 2018
Abstract During the past decade, the dramatic increase in the computational capabilities of chip processing and the lower costs of computing hardware have led to the emergence of deep learning, which refers to a sub-field of machine learning that focuses on learning features extracted from data and classifying them through multiple layers in the hierarchical architectures of neural networks. Using convolution neural networks (CNN) is one of the most promising deep learning methods for dealing with several pattern recognition tasks. However, as with most artificial neural networks, CNNs are susceptible to multiple local optima. Hence, in order to avoid becoming trapped within the local optima, improvement of the CNNs is thus required. The optimization methods based on a metaheuristic are very powerful in solving optimization problems. However, research on the use of metaheuristics to optimize CNNs is rarely conducted. In this work, the artificial bee colony (ABC) method, one of the most popular metaheuristic methods, is proposed as an alternative approach to optimizing the performance of a CNN. In other words, we aim to minimize the classification errors by initializing the weights of the CNN classifier based on solutions generated by the ABC method. Moreover, the distributed ABC is also presented as a method to maintain the amount of time needed to execute the process when working with large training datasets. The results of the experiment demonstrate that the proposed method can improve the performance of the ordinary CNNs in both recognition accuracy and computing time. Keywords Deep learning · Convolution neural networks · Distributed artificial bee colony · Pattern recognition · Classification
1 Introduction Deep learning [1] is a set of methods in a sub-field of machine learning that has been developed for training multilayered artificial neural networks. It has been found to be especially effective in identifying patterns found in datasets. Over the past decade, deep learning has become a more interesting and powerful method with great success in many domains, such as image and speech recognition, computer vision, and natural language processing [2–7]. Methods of deep learning can be categorized into two approaches, deep generative approaches and discriminative approaches [8]. In the deep generative approach, a joint distribution is modeled * Anan Banharnsakun [email protected] 1
Computational Intelligence Research Laboratory (CIRLab), Computer Engineering Department, Faculty of Engineering at Sriracha, Kasetsart University Sriracha Campus, Chonburi 20230, Thailand
on inputs and outputs, and the parameters are typically estimated using a likelihood-based criterion; whereas in the discriminative approach, the mapping is directly modeled fr
Data Loading...
