C Raymond - arXiv preprint arXiv:2406.09713, 2024 - arxiv.org
Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require …
C So - 2021 International Conference on Artificial Intelligence …, 2021 - ieeexplore.ieee.org
Meta-learning has emerged as a new paradigm in AI to challenge the limitation of conventional deep learning to acquire only task-specific knowledge. Meta-learning …
To benefit the learning of a new task, meta-learning has been proposed to transfer a well- generalized meta-model learned from various meta-training tasks. Existing meta-learning …
Z Wang, X Wang, L Shen, Q Suo… - Uncertainty in …, 2022 - proceedings.mlr.press
Existing meta-learning works assume that each task has available training and testing data. However, there are many available pre-trained models without accessing their training data …
Deep neural networks can yield good performance on various tasks but often require large amounts of data to train them. Meta-learning received considerable attention as one …
Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm that provides good weight initialization of a model given a variety of learning tasks. The …
Inspired by optimization techniques, we propose a novel meta-learning algorithm with gradient modulation to encourage fast-adaptation of neural networks in the absence of …
Y Ding, Y Wu, C Huang, S Tang… - Proceedings of the …, 2022 - openaccess.thecvf.com
Meta-learning enables models to adapt to new environments rapidly with a few training examples. Current gradient-based meta-learning methods concentrate on finding good …
J Wang, W Qiang, X Su, C Zheng, F Sun… - International Journal of …, 2024 - Springer
Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task …