Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks

Amri, A’inur A’fifah and Ismail, Amelia Ritahani and Abdullah, Ahmad Zarir (2016) Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks. In: The 3rd International Multi-Conference on Artificial Intelligence Technology (M-CAIT 2016), 23rd-24th August 2016, Malacca, Malaysia. (Unpublished)

PDF - Published Version Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Imbalanced class is one of the challenges in classifying big data. Data disparity produces a biased output of a model regardless how recent the technology is. However, deep learning algorithms such as convolutional neural networks and deep belief networks showed promising results in many domains, especially in image processing. Therefore, in this paper, we will review the effect of imbalanced data disparity in classes using convolutional neural networks and deep belief networks as the benchmark model, and a modified MNIST handwritten dataset as the bench- mark dataset. The experiment shows that although the algorithm is stable and suitable for multiple domains, the imbalanced data distribution still manages to affect the outcome of the model.

Item Type:	Conference or Workshop Item (Plenary Papers)
Additional Information:	4296/53436
Uncontrolled Keywords:	convolutional neural networks; deep belief networks; imbalanced class
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology > Department of Computer Science Kulliyyah of Information and Communication Technology > Department of Computer Science
Depositing User:	Amelia Ritahani Ismail
Date Deposited:	21 Dec 2016 09:00
Last Modified:	21 Dec 2016 09:00
URI:	http://irep.iium.edu.my/id/eprint/53436

Actions (login required)

View Item