no code implementations • 20 Apr 2024 • Ahmadreza Eslaminia, Yuquan Meng, Klara Nahrstedt, Chenhui Shao
Recently, machine learning models emerged as a promising tool for CM in many manufacturing applications due to their ability to learn complex patterns.
1 code implementation • 31 Jan 2024 • Hongpeng Guo, Haotian Gu, Xiaoyang Wang, Bo Chen, Eun Kyung Lee, Tamar Eilam, Deming Chen, Klara Nahrstedt
Federated learning (FL) is a machine learning paradigm that allows multiple clients to collaboratively train a shared model while keeping their data on-premise.
no code implementations • 5 Aug 2023 • Beitong Tian, Kuan-Chieh Lu, Ahmadreza Eslaminia, Yaohui Wang, Chenhui Shao, Klara Nahrstedt
Ultrasonic welding machines play a critical role in the lithium battery industry, facilitating the bonding of batteries with conductors.
1 code implementation • 24 Jul 2022 • Gaoang Wang, Yibing Zhan, Xinchao Wang, Mingli Song, Klara Nahrstedt
Anomaly detection aims at identifying deviant samples from the normal data distribution.
no code implementations • 29 Sep 2021 • Xiaoyang Wang, Han Zhao, Klara Nahrstedt, Oluwasanmi O Koyejo
To this end, we propose a strategy to mitigate the effect of spurious features based on our observation that the global model in the federated learning step has a low accuracy disparity due to statistical heterogeneity.
no code implementations • 13 May 2021 • Hongpeng Guo, Shuochao Yao, Zhe Yang, Qian Zhou, Klara Nahrstedt
Video cameras are pervasively deployed in city scale for public good or community safety (i. e. traffic monitoring or suspected person tracking).
no code implementations • 5 May 2021 • Zhe Yang, Klara Nahrstedt, Hongpeng Guo, Qian Zhou
Based on this analysis, we propose a GPU scheduler, DeepRT, which provides latency guarantee to the requests while maintaining high overall system throughput.
no code implementations • 15 Jan 2021 • Xiaoyang Wang, Bo Li, Yibo Zhang, Bhavya Kailkhura, Klara Nahrstedt
However, these AutoML pipelines only focus on improving the learning accuracy of benign samples while ignoring the ML model robustness under adversarial attacks.
1 code implementation • 1st Conference on Causal Learning and Reasoning 2022 • Xiaoyang Wang, Klara Nahrstedt, Oluwasanmi O Koyejo
Current approaches for learning disentangled representations assume that independent latent variables generate the data through a single data generation process.
no code implementations • 12 May 2020 • Tarek Elgamal, Klara Nahrstedt
To address this challenge, we present Serdab, a distributed orchestration framework for deploying deep neural network computation across multiple secure enclaves (e. g., Intel SGX).