Results 101 to 110 of about 24,131 (257)

Probing Machine Learning Interatomic Potentials on Ion Transport Properties

Advanced Intelligent Discovery, EarlyView.
We perform a systematic benchmark of six state‐of‐the‐art universal machine learning interatomic potentials on their ability to predict ion transport properties in lithium‐ and sodium‐based superionic conductors relevant to all‐solid‐state batteries.
Ogheneyoma Aghoghovbia, Ming Hu, Adji Bousso Dieng   +2 more
wiley   +1 more source

Outlook towards deployable continual learning for particle accelerators

Machine Learning: Science and Technology
Particle accelerators are high power complex machines. To ensure uninterrupted operation of these machines, thousands of pieces of equipment need to be synchronized, which requires addressing many challenges including design, optimization and control ...
Kishansingh Rajput, Sen Lin, Auralee Edelen, Willem Blokland, Malachi Schram   +4 more
doaj   +1 more source

Design, Control, and Clinical Applications of Magnetic Actuation Systems: Challenges and Opportunities

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
This review aims to provide a broad understanding for interdisciplinary researchers in engineering and clinical applications. It addresses the development and control of magnetic actuation systems (MASs) in clinical surgeries and their revolutionary effects in multiple clinical applications.
Yingxin Huo, Lidong Yang, Tiantian Xu, Dong Sun   +3 more
wiley   +1 more source

3D-AOCL: Analytic online continual learning for imbalanced 3D point cloud classification

Alexandria Engineering Journal
Recent autonomous driving systems heavily rely on 3D point cloud data collected from multiple sensors for environmental awareness and decision-making. However, it is unrealistic to expect the autonomous driving system to recognize all road environments ...
Ziqian Zeng, Jianwei Wang, Lin Wu, Weikai Lu, Huiping Zhuang   +4 more
doaj   +1 more source

Continual graph learning: A survey

Pattern Recognition
Continual Graph Learning (CGL) enables models to incrementally learn from streaming graph-structured data without forgetting previously acquired knowledge. Experience replay is a common solution that reuses a subset of past samples during training. However, it may lead to information loss and privacy risks. Generative replay addresses these concerns by
Qiao Yuan, Sheng-Uei Guan, Pin Ni, Tianlun Luo, Prudence Wong, Victor Chang, Ka Lok Man   +6 more
openaire   +2 more sources

Continual Unsupervised Representation Learning

CoRR, 2019
NeurIPS ...
Rao, D, Visin, F, Rusu, AA, Teh, YW, Pascanu, R, Hadsell, R   +5 more
openaire   +4 more sources

Master narratives as “colonial propaganda” and counternarratives as “refusal”: How African Australians reimagine racial dignity in Australia

American Journal of Community Psychology, EarlyView.
Abstract This paper utilizes the concept of “colonial master narratives” to examine how racial propaganda is mobilized in the Australian imaginary to “flatten” the stories of Blac/k people and how African Australians deploy counternarratives to reject these racialized projections.
Kathomi Gatwiri, Samara Kim
wiley   +1 more source

PRCSL: A privacy-preserving continual split learning framework for decentralized medical diagnosis

Machine Learning with Applications
Deep learning-based medical AI systems are increasingly deployed for disease diagnosis in decentralized healthcare environments where data are siloed across hospitals and IoT devices and cannot be freely shared due to strict privacy and security ...
Jungmin Eom, Minjun Kang, Myungkeun Yoon, Nikil Dutt, Jinkyu Kim, Jaekoo Lee   +5 more
doaj   +1 more source

Continual learning in the presence of repetition

Neural Networks
Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not often considered in standard benchmarks for CL.
Hamed Hemati, Lorenzo Pellegrini, Xiaotian Duan, Zixuan Zhao, Fangfang Xia, Marc Masana, Benedikt Tscheschner, Eduardo E. Veas, Yuxiang Zheng, Shiji Zhao, Shao-Yuan Li, Sheng-Jun Huang, Vincenzo Lomonaco, Gido M. van de Ven   +13 more
openaire   +5 more sources

Freedom dreaming of migrant justice: Critical reflections on counterspaces and institutional violence in the university

American Journal of Community Psychology, EarlyView.
Abstract US universities are built on stolen land and sustained through hierarchies of power that produce what migrant justice scholars name as b/order regimes. As institutions that claim to be sites of learning and inclusion, universities are fraught with contradictions as simultaneously sites of dispossession, exclusion, and control.
Sara L. Buckingham, Jesica Siham Fernández   +1 more
wiley   +1 more source