Results 121 to 130 of about 151,060 (281)

Sleep-like unsupervised replay reduces catastrophic forgetting in artificial neural networks. [PDF]

Nat Commun, 2022
Tadros T, Krishnan GP, Ramyaa R, Bazhenov M.   +3 more
europepmc   +1 more source

Network Latency Estimation for Telesurgery Using Deep Reinforcement Learning

SmartBot, EarlyView.
Overview of the proposed two‐stage deep reinforcement learning framework for network latency prediction in telesurgery. The pipeline includes data collection from simulated catheter navigation sessions (Philippines–Botswana), feature engineering, DQN‐based direction prediction (85.8% accuracy), direction‐to‐value transformation, and value forecasting ...
Bakang Kgopolo, Rodrigo S. Jamisola Jr., Molaletsa Namoshe   +2 more
wiley   +1 more source

CIELO: Class-Incremental Continual Learning for Overcoming Catastrophic Forgetting With Smartphone-Based Indoor Localization

IEEE Access
With dynamically evolving indoor environments, class-incremental learning (CIL) plays a crucial role in enabling indoor localization systems to adapt to new indoor areas.
Akhil Singampalli, Danish Gufran, Sudeep Pasricha   +2 more
doaj   +1 more source

When Time Stands Still: The Destructive Experience of Ambiguous Loss among Mothers of Combat Soldiers

Symbolic Interaction, EarlyView.
What happens when stories refuse coherence? This article examines ambiguous loss among mothers of combat soldiers, focusing on how prolonged waiting and uncertainty infiltrate everyday life, eroding sensemaking. Drawing on ethnographic interviews, it explores how mothers experience the contraction of time and space—manifested in suspended routines ...
Shirly Bar‐Lev, Galit Itzhaki Draizin, Agamit Gelb   +2 more
wiley   +1 more source

Brain-inspired memory architecture for condition monitoring based on hippocampal-neocortical complementary learning

High-Speed Railway
This paper tackles the critical challenge of catastrophic forgetting and inefficient learning in artificial intelligence models processing continuous, non-stationary data streams.
Yue Yu, Zeyun Yang, Xiaohui Zhang, Xinkang Li, Jianhui Yi, Deshui Han   +5 more
doaj   +1 more source

Robust Multi‐Source Batch Normalisation for Test‐Time Batch Adaptation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Test‐Time Batch Adaptation (TTBA) aims to adapt a pre‐trained source model to small, unlabelled target batches at test time. The TTBA methods focus on adapting the pre‐trained model or the target data in a one‐to‐one alignment paradigm. However, these one‐to‐one alignment paradigms assume that the source domain may share the same knowledge ...
Xinlin Xiao, Xiangtao Zheng, Jianhua Tao, Xiaoqiang Lu   +3 more
wiley   +1 more source

Hyperbolic Prototype Guidance for Incremental SAR ATR

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Despite the success of deep learning methods in synthetic aperture radar automatic target recognition (SAR ATR), they face significant challenges in open environments. Deep models suffer from catastrophic forgetting when learning new classes.
Yanjie Xu, Hao Sun, Chenfang Liu, Linbin Zhang, Kefeng Ji, Gangyao Kuang   +5 more
doaj   +1 more source

A Validation Method for the Enhanced Fuzzy Min‐Max Neural Network With Application to Heart Disease Data Classification

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT This study investigates early detection of heart diseases using a new Enhanced Fuzzy Min‐Max (EFMM) neural network. Two key modifications are introduced: a refined EFMM contraction procedure during the learning phase to reduce data distortion and information loss, and a new weighted validation method to optimise hyperbox selection and improve ...
Mohammed Falah Mohammed, Osama Nayel Al Sayaydeh, Taha H. Rassem, Chee Peng Lim   +3 more
wiley   +1 more source

Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging. [PDF]

Nat Commun, 2021
Perkonigg M, Hofmanninger J, Herold CJ, Brink JA, Pianykh O, Prosch H, Langs G.   +6 more
europepmc   +1 more source

Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Accepted by ...
Wei Huang 0039, Anda Cheng, Yinggui Wang
openaire   +2 more sources