no code implementations • 15 Nov 2023 • Sin Cheng Ciou, Pin Jui Chen, Elvin Y. Tseng, Yuh-Jye Lee
The federated learning framework addresses this challenge.
no code implementations • 1 Jan 2021 • Yen-Chieh Huang, Yuh-Jye Lee, Chih-Chi Wu, Yi-Wei Chiu, Yong-Xiang Lin, CHENG-YING LI, Po-Hung Ko
We proposed a novel loss function that combines supervised learning with clustering in deep neural networks.
1 code implementation • 11th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems 2013 • Yi-Ren Yeh, Zheng-Yi Lee, Yuh-Jye Lee
Based on this idea, an over-sampling principal component analysis outlier detection method is proposed for emphasizing the influence of an abnormal instance (or an outlier).
Ranked #1 on Anomaly Detection on kdd 99
no code implementations • NeurIPS 2009 • Chun-Nan Hsu, Yu-Ming Chang, Hanshen Huang, Yuh-Jye Lee
It has been established that the second-order stochastic gradient descent (2SGD) method can potentially achieve generalization performance as well as empirical optimum in a single pass (i. e., epoch) through the training examples.