Zobrazeno 1 - 10
of 18 189
pro vyhledávání: '"Vinod, K"'
Deep neural networks trained on biased data often inadvertently learn unintended inference rules, particularly when labels are strongly correlated with biased features. Existing bias mitigation methods typically involve either a) predefining bias typ
Externí odkaz:
http://arxiv.org/abs/2410.15094
Autor:
Oli, Tupendra, Olin-Ammentorp, Wilkie, Wu, Xingfu, Qian, Justin H., Sangwan, Vinod K., Hersam, Mark C., Habib, Salman, Taylor, Valerie
As particle physics experiments evolve to achieve higher energies and resolutions, handling the massive data volumes produced by silicon pixel detectors, which are used for charged particle tracking, poses a significant challenge. To address the chal
Externí odkaz:
http://arxiv.org/abs/2409.13933
In machine learning applications, gradual data ingress is common, especially in audio processing where incremental learning is vital for real-time analytics. Few-shot class-incremental learning addresses challenges arising from limited incoming data.
Externí odkaz:
http://arxiv.org/abs/2407.19265
Autor:
Wu, Xingfu, Oli, Tupendra, Qian, Justin H., Taylor, Valerie, Hersam, Mark C., Sangwan, Vinod K.
Support Vector Machine (SVM) is a state-of-the-art classification method widely used in science and engineering due to its high accuracy, its ability to deal with high dimensional data, and its flexibility in modeling diverse sources of data. In this
Externí odkaz:
http://arxiv.org/abs/2406.18445
AI algorithms at the edge demand smaller model sizes and lower computational complexity. To achieve these objectives, we adopt a green learning (GL) paradigm rather than the deep learning paradigm. GL has three modules: 1) unsupervised representation
Externí odkaz:
http://arxiv.org/abs/2312.14968
Autor:
Shi, Jiacheng, Lopez-Dominguez, Victor, Arpaci, Sevdenur, Sangwan, Vinod K., Mahfouzi, Farzad, Kim, Jinwoong, Athas, Jordan G., Hamdi, Mohammad, Aygen, Can, Phatak, Charudatta, Carpentieri, Mario, Jiang, Jidong S., Grayson, Matthew A., Kioussis, Nicholas, Finocchio, Giovanni, Hersam, Mark C., Amiri, Pedram Khalili
Antiferromagnetic (AFM) materials are a pathway to spintronic memory and computing devices with unprecedented speed, energy efficiency, and bit density. Realizing this potential requires AFM devices with simultaneous electrical writing and reading of
Externí odkaz:
http://arxiv.org/abs/2311.13828