Convolutional neural networks and deep belief networks for analysing imbalanced class issue in handwritten dataset

• Main Authors: Amri, A’inur A’fifah, Ismail, Amelia Ritahani, Zarir, Abdullah Ahmad
• 格式: Article
• 语言: English; English
• 出版: INSIGHT - Indonesian Society for Knowledge and Human Development 2017
• 主题: QA75 Electronic computers. Computer science
• 在线阅读: 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; http://irep.iium.edu.my/62150/; http://www.insightsociety.org/ojaseit/index.php/ijaseit/article/view/2632/pdf_614

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...