Results 21 to 30 of about 259,517 (255)
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
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
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
Automated data pre-processing via meta-learning [PDF]
, 2016 The final publication is available at link.springer.comA data mining algorithm may perform differently on datasets with different characteristics, e.g., it might perform better on a dataset with continuous attributes rather than with categorical ...
A Guazzelli +9 more
core +1 more source
Pairwise meta-rules for better meta-learning-based algorithm ranking [PDF]
, 2013 In this paper, we present a novel meta-feature generation method in the context of meta-learning, which is based on rules that compare the performance of individual base learners in a one-against-one manner.
Pfahringer, Bernhard, Sun, Quan
core +2 more sources
Generalization of Forgery Detection With Meta Deepfake Detection Model
IEEE Access, 2023 Face forgery generating algorithms that produce a range of manipulated videos/images have developed quickly. Consequently, this causes an increase in the production of fake information, making it difficult to identify.
Van-Nhan Tran +4 more
doaj +1 more source
, 2019 Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible.
openaire +2 more sources
Learning with few samples in deep learning for image classification, a mini-review
Frontiers in Computational Neuroscience, 2023 Deep learning has achieved enormous success in various computer tasks. The excellent performance depends heavily on adequate training datasets, however, it is difficult to obtain abundant samples in practical applications.
Rujun Zhang, Qifan Liu
doaj +1 more source
A Meta Learning-Based Approach for Zero-Shot Co-Training
IEEE Access, 2021 The lack of labeled data is one of the main obstacles to the application of machine learning algorithms in a variety of domains. Semi-supervised learning, where additional samples are automatically labeled, is a common and cost-effective approach to ...
Guy Zaks, Gilad Katz
doaj +1 more source