Results 21 to 30 of about 83,974 (281)
One-Shot Fault Diagnosis of Wind Turbines Based on Meta-Analogical Momentum Contrast Learning
Energies, 2022 The rapid development of artificial intelligence offers more opportunities for intelligent mechanical diagnosis. Fault diagnosis of wind turbines is beneficial to improve the reliability of wind turbines.
Xiaobo Liu, Hantao Guo, Yibing Liu
doaj +1 more source
Calibration of Few-Shot Classification Tasks: Mitigating Misconfidence From Distribution Mismatch
IEEE Access, 2022 As many meta-learning algorithms improve performance in solving few-shot classification problems for practical applications, the accurate prediction of uncertainty is considered essential.
Sungnyun Kim, Se-Young Yun
doaj +1 more source
Uncertainty in Model-Agnostic Meta-Learning using Variational Inference [PDF]
2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020 We introduce a new, rigorously-formulated Bayesian meta-learning algorithm that learns a probability distribution of model parameter prior for few-shot learning. The proposed algorithm employs a gradient-based variational inference to infer the posterior of model parameters to a new task.
Nguyen, Cuong +2 more
openaire +2 more sources
Scientific Reports, 2023 To increase the accuracy of medical image analysis using supervised learning-based AI technology, a large amount of accurately labeled training data is required.
Yeongjoon Kim +4 more
doaj +1 more source
Information-Theoretic Generalization Bounds for Meta-Learning and Applications
Entropy, 2021 Meta-learning, or “learning to learn”, refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks.
Sharu Theresa Jose, Osvaldo Simeone
doaj +1 more source
Model-Agnostic Meta-Learning for Fault Diagnosis of Industrial Robots
2023 28th International Conference on Automation and Computing (ICAC), 2023 The success of deep learning in the field of fault diagnosis depends on a large number of training data, but it is a challenge to achieve fault diagnosis of multi-axis industrial robots in the case of few-shot. To address this issue, this paper proposes a method called Model-Agnostic Meta-Learning (MAML) for fault diagnosis of industrial robots.
Liu, Yuxin +4 more
openaire +2 more sources
Applied Sciences, 2023 In the field of intelligent anti-jamming, deep reinforcement learning algorithms are regarded as key technical means. However, the learning process of deep reinforcement learning algorithms requires a stable learning environment to ensure its ...
Qingchuan Chen +3 more
doaj +1 more source
Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum Algorithms [PDF]
AAAI Conference on Artificial IntelligenceIn the Noisy Intermediate-Scale Quantum (NISQ) era, using variational quantum algorithms (VQAs) to solve optimization problems has become a key application.
Junyong Lee, Jeihee Cho, Shiho Kim
semanticscholar +1 more source
Picking groups instead of samples: a close look at Static Pool-based Meta-Active Learning [PDF]
, 2019 ©2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new ...
Mas Méndez, Ignasi +2 more
core +2 more sources
Task-Robust Model-Agnostic Meta-Learning
, 2020 Meta-learning methods have shown an impressive ability to train models that rapidly learn new tasks. However, these methods only aim to perform well in expectation over tasks coming from some particular distribution that is typically equivalent across meta-training and meta-testing, rather than considering worst-case task performance.
Collins, Liam +2 more
openaire +2 more sources