Comparative performance of deep learning and machine learning algorithms on imbalanced handwritten data

• 主要な著者: Amri, A’inur A’fifah, Ismail, Amelia Ritahani, Zarir, Abdullah Ahmad
• フォーマット: 論文
• 言語: English; English; English
• 出版事項: The Science and Information (SAI) Organization 2018
• 主題: QA75 Electronic computers. Computer science
• オンライン･アクセス: http://irep.iium.edu.my/62456/7/62456-Comparative%20performance%20of%20deep%20learning%20_scopus.pdf; http://irep.iium.edu.my/62456/8/62456-Comparative%20Performance%20of%20Deep%20Learning_%20article.pdf; http://irep.iium.edu.my/62456/19/62456_Comparative%20performance%20of%20deep%20learning_WOS.pdf; http://irep.iium.edu.my/62456/; http://thesai.org/Downloads/Volume9No2/Paper_36-Comparative_Performance_of_Deep_Learning.pdf

Imbalanced data is one of the challenges in a classification task in machine learning. Data disparity produces a biased output of a model regardless how recent the technology is. However, deep learning algorithms, such as deep belief networks showed promising results in many domains, especially in...