Zobrazeno 1 - 10
of 289
pro vyhledávání: '"Gao, Yuyang"'
Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model. However, the app
Externí odkaz:
http://arxiv.org/abs/2403.10831
The widespread consumer-grade 3D printers and learning resources online enable novices to self-train in remote settings. While troubleshooting plays an essential part of 3D printing, the process remains challenging for many remote novices even with t
Externí odkaz:
http://arxiv.org/abs/2401.15877
Federated learning (FL) is a distributed machine learning (ML) paradigm, allowing multiple clients to collaboratively train shared machine learning (ML) models without exposing clients' data privacy. It has gained substantial popularity in recent yea
Externí odkaz:
http://arxiv.org/abs/2308.05014
Autor:
Sun, Tong Steven, Gao, Yuyang, Khaladkar, Shubham, Liu, Sijia, Zhao, Liang, Kim, Young-Ho, Hong, Sungsoo Ray
The local explanation provides heatmaps on images to explain how Convolutional Neural Networks (CNNs) derive their output. Due to its visual straightforwardness, the method has been one of the most popular explainable AI (XAI) methods for diagnosing
Externí odkaz:
http://arxiv.org/abs/2307.04036
Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful strategies
Externí odkaz:
http://arxiv.org/abs/2212.13242
We consider a slow-fast Hamiltonian system with one fast angular variable (a fast phase) whose frequency vanishes on some surface in the space of slow variables (a resonant surface). Systems of such form appear in the study of dynamics of charged par
Externí odkaz:
http://arxiv.org/abs/2212.13293
As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing DNNs become more complex and diverse, ranging from improving a conventional model accuracy metric to infusing advanced human virtues such as fairness, accountability
Externí odkaz:
http://arxiv.org/abs/2212.03954
Publikováno v:
In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '22), August 14-18, 2022, Washington, DC, USA
Despite the fast progress of explanation techniques in modern Deep Neural Networks (DNNs) where the main focus is handling "how to generate the explanations", advanced research questions that examine the quality of the explanation itself (e.g., "whet
Externí odkaz:
http://arxiv.org/abs/2206.13413
While Deep Neural Networks (DNNs) are deriving the major innovations in nearly every field through their powerful automation, we are also witnessing the peril behind automation as a form of bias, such as automated racism, gender bias, and adversarial
Externí odkaz:
http://arxiv.org/abs/2202.02838
Autor:
Gao, Yuyang1 (AUTHOR) ygao13.personal@gmail.com, Gu, Siyi1 (AUTHOR) carrie.gu@emory.edu, Jiang, Junji1 (AUTHOR) jjian50@emory.edu, Hong, Sungsoo Ray2 (AUTHOR) shong31@gmu.edu, Yu, Dazhou1 (AUTHOR) dazhou.yu@emory.edu, Zhao, Liang1 (AUTHOR) liang.zhao@emory.edu
Publikováno v:
ACM Computing Surveys. Jul2024, Vol. 56 Issue 7, p1-39. 39p.