Convolutional neural networks and deep belief networks for analysing imbalanced class issue in handwritten dataset
Imbalanced class is one of the trials in classifying materials of 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 have proven to provide promising...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
INSIGHT - Indonesian Society for Knowledge and Human Development
2017
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/62150/ http://irep.iium.edu.my/62150/ http://irep.iium.edu.my/62150/1/Convolutional%20Neural%20Networks%20and%20Deep%20Belief%20Networks.pdf http://irep.iium.edu.my/62150/7/62150_Convolutional%20Neural%20Networks%20and%20Deep%20Belief%20Networks_scopus.pdf |
| Summary: | Imbalanced class is one of the trials in classifying materials of 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 have proven to provide promising results in many research domains,
especially in image processing as well as time series forecasting, intrusion detection, and classification. Therefore, this
paper will investigate the effect of imbalanced data discrepancy of classes in MNIST handwritten dataset using
convolutional neural networks and deep belief networks. Based on the experiment conducted, the results show that
although the algorithm is suitable for multiple domains and have shown stability, the imbalanced distribution of data
still able to affect the overall performance of the models. |
|---|