Results 21 to 30 of about 252,836 (257)
Remote Sensing, 2021 The performance of deep learning is heavily influenced by the size of the learning samples, whose labeling process is time consuming and laborious.
Yong Li +4 more
doaj +1 more source
CoRR, 2019 Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model applicable to the tasks with new structures, it is required to collect new training data and repeat the time-consuming ...
Yingtian Zou, Jiashi Feng
openaire +2 more sources
CoRR, 2020 Meta-learning leverages related source tasks to learn an initialization that can be quickly fine-tuned to a target task with limited labeled examples. However, many popular meta-learning algorithms, such as model-agnostic meta-learning (MAML), only assume access to the target samples for fine-tuning.
Diana Cai +3 more
openaire +2 more sources
Meta-learning with Network Pruning [PDF]
, 2020 Meta-learning is a powerful paradigm for few-shot learning. Although with remarkable success witnessed in many applications, the existing optimization based meta-learning models with over-parameterized neural networks have been evidenced to ovetfit on training tasks.
Hongduan Tian +3 more
openaire +2 more sources
A Contrastive Rule for Meta-Learning
Advances in Neural Information Processing Systems 35, 2022 Meta-learning algorithms leverage regularities that are present on a set of tasks to speed up and improve the performance of a subsidiary learning process. Recent work on deep neural networks has shown that prior gradient-based learning of meta-parameters can greatly improve the efficiency of subsequent learning.
Zucchet, Nicolas +4 more
openaire +4 more sources
Entropy, 2023 This paper proposes an air combat training framework based on hierarchical reinforcement learning to address the problem of non-convergence in training due to the curse of dimensionality caused by the large state space during air combat tactical pursuit.
Ruihai Chen +4 more
doaj +1 more source
Towards Explainable Meta-learning [PDF]
, 2021 Meta-learning is a field that aims at discovering how different machine learning algorithms perform on a wide range of predictive tasks. Such knowledge speeds up the hyperparameter tuning or feature engineering. With the use of surrogate models various aspects of the predictive task such as meta-features, landmarker models e.t.c.
Katarzyna Woznica, Przemyslaw Biecek
openaire +2 more sources
Federated meta learning: a review
大数据, 2023 With the popularity of mobile devices, massive amounts of data are constantly produced.The data privacy policies are becoming more and more specified, the flow and use of data are strictly regulated.Federated learning can break data barriers and use ...
Chuanyao ZHANG +3 more
doaj
CoRR, 2019 Clustering is one of the most fundamental and wide-spread techniques in exploratory data analysis. Yet, the basic approach to clustering has not really changed: a practitioner hand-picks a task-specific clustering loss to optimize and fit the given data to reveal the underlying cluster structure.
Yibo Jiang, Nakul Verma
openaire +2 more sources
Meta-learning of Textual Representations [PDF]
, 2020 Recent progress in AutoML has lead to state-of-the-art methods (e.g., AutoSKLearn) that can be readily used by non-experts to approach any supervised learning problem. Whereas these methods are quite effective, they are still limited in the sense that they work for tabular (matrix formatted) data only. This paper describes one step forward in trying to
Jorge G. Madrid +2 more
openaire +2 more sources