Results 11 to 20 of about 83,974 (281)
Alpha MAML: Adaptive Model-Agnostic Meta-Learning
, 2019 Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks.
Baydin, Atılım Güneş +2 more
core +3 more sources
Enhancing Model Agnostic Meta-Learning via Gradient Similarity Loss
ElectronicsArtificial intelligence (AI) technology has advanced significantly, now capable of performing tasks previously believed to be exclusive to skilled humans.
Jae-Ho Tak, Byung-Woo Hong
semanticscholar +2 more sources
Few-Shot Bearing Fault Diagnosis Based on Model-Agnostic Meta-Learning [PDF]
IEEE transactions on industry applications, 2020 The rapid development of artificial intelligence and deep learning has provided many opportunities to further enhance the safety, stability, and accuracy of industrial cyber-physical systems (CPS). As indispensable components to many mission-critical CPS
Shen Zhang +3 more
semanticscholar +1 more source
Multi-Agent Chronological Planning with Model-Agnostic Meta Reinforcement Learning
Applied Sciences, 2023 In this study, we propose an innovative approach to address a chronological planning problem involving the multiple agents required to complete tasks under precedence constraints.
Cong Hu +4 more
doaj +1 more source
Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?
, 2022 Meta learning aims at learning a model that can quickly adapt to unseen tasks. Widely used meta learning methods include model agnostic meta learning (MAML), implicit MAML, Bayesian MAML. Thanks to its ability of modeling uncertainty, Bayesian MAML often has advantageous empirical performance.
Chen, Lisha, Chen, Tianyi
openaire +2 more sources
Speaker Adaptive Training Using Model Agnostic Meta-Learning [PDF]
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019 Accepted to IEEE ASRU ...
Klejch, Ondrej +3 more
openaire +3 more sources
Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 In this paper, we develop upon the emerging topic of loss function learning, which aims to learn loss functions that significantly improve the performance of the models trained under them. Specifically, we propose a new meta-learning framework for learning model-agnostic loss functions via a hybrid neuro-symbolic search approach.
Christian Raymond +3 more
openaire +3 more sources
Memory-augmented meta-learning on meta-path for fast adaptation cold-start recommendation
Connection Science, 2022 Personalised recommendation is a difficult problem that has received a lot of attention to academia and industry. Because of the sparse user–item interaction, cold-start recommendation has been a particularly difficult problem.
Tianyuan Li +7 more
doaj +1 more source
Cross Domain Adaptation of Crowd Counting with Model-Agnostic Meta-Learning
Applied Sciences, 2021 Counting people in crowd scenarios is extensively conducted in drone inspections, video surveillance, and public safety applications. Today, crowd count algorithms with supervised learning have improved significantly, but with a reliance on a large ...
Xiaoyu Hou +3 more
doaj +1 more source
Model-Agnostic Learning to Meta-Learn
Proceedings of Machine Learning Research, 148:155–175, 2021, 2020 In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate how learning with different task distributions can first improve adaptability by meta-finetuning on related tasks
Devos, Arnout, Dandi, Yatin
openaire +2 more sources