https://scholars.lib.ntu.edu.tw/handle/123456789/581364
標題: | Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation | 作者: | Chung Y.-A Yang S.-W HSUAN-TIEN LIN |
關鍵字: | Cost estimating; Deep neural networks; Neural networks; Object detection; Speech recognition; Classification accuracy; Cost estimations; Cost information; Cost sensitive classifications; Learning models; Misclassification error; Network structures; State of the art; Deep learning | 公開日期: | 2020 | 起(迄)頁: | 108-113 | 來源出版物: | Proceedings - 25th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2020 | 摘要: | While deep neural networks have succeeded in several applications, such as image classification, object detection, and speech recognition, by reaching very high classification accuracies, it is important to note that many real-world applications demand varying costs for different types of misclassification errors, thus requiring cost-sensitive classification algorithms. Current models of deep neural networks for cost-sensitive classification are restricted to some specific network structures and limited depth. In this paper, we propose a novel framework that can be applied to deep neural networks with any structure to facilitate their learning of meaningful representations for cost-sensitive classification problems. Furthermore, the framework allows end-to-end training of deeper networks directly. The framework is designed by augmenting auxiliary neurons to the output of each hidden layer for layer-wise cost estimation, and including the total estimation loss within the optimization objective. Experimental results on public benchmark data sets with two cost information settings demonstrate that the proposed framework outperforms state-of-the-art cost-sensitive deep learning models. ? 2020 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85103812376&doi=10.1109%2fTAAI51410.2020.00028&partnerID=40&md5=bb2a43d3b4440ef3b50027e9fb62c3f0 https://scholars.lib.ntu.edu.tw/handle/123456789/581364 |
DOI: | 10.1109/TAAI51410.2020.00028 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。