Information set supported deep learning architectures for improving noisy image classification

• Published in: Scientific reports Vol. 13; no. 1; p. 4417
• Main Authors: Bhardwaj, Saurabh, Wang, Yizhi, Yu, Guoqiang, Wang, Yue
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 17-03-2023; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/1042; 639/705/117; Classification; Datasets; Deep learning; Design; Fuzzy sets; Humanities and Social Sciences; Information sources; multidisciplinary; Neural networks; Science; Science (multidisciplinary); Set theory; Signal to noise ratio
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-31462-6

Deep learning models have been widely used in many supervised learning applications. However, these models suffer from overfitting due to various types of uncertainty with deteriorating performance when facing data biases, class imbalance, or noise propagation. The Information-Set Deep learning (ISDL) architectures with four variants are developed by integrating information set theory and deep learning principles to address the critical problem of the absence of robust deep learning models. There is a description of the ISDL architectures, learning algorithms, and analytic workflows. The performance of the ISDL models and standard architectures is evaluated using a noise-corrupted benchmark dataset. The experimental results show that the ISDL models can efficiently handle noise-dominated uncertainty and outperform peer architectures.