Semi-supervised learning by disagreement
In many real-world tasks, there are abundant unlabeled examples but the number of labeled
training examples is limited, because labeling the examples requires human efforts and …
training examples is limited, because labeling the examples requires human efforts and …
[PDF][PDF] 基于分歧的半监督学习
周志华 - 自动化学报, 2013 - aas.net.cn
摘要传统监督学习通常需使用大量有标记的数据样本作为训练例, 而在很多现实问题中,
人们虽能容易地获得大批数据样本, 但为数据提供标记却需耗费很多人力物力. 那么 …
人们虽能容易地获得大批数据样本, 但为数据提供标记却需耗费很多人力物力. 那么 …
When semi-supervised learning meets ensemble learning
ZH Zhou - Frontiers of Electrical and Electronic Engineering in …, 2011 - Springer
Semi-supervised learning and ensemble learning are two important machine learning
paradigms. The former attempts to achieve strong generalization by exploiting unlabeled …
paradigms. The former attempts to achieve strong generalization by exploiting unlabeled …
CoTrade: Confident co-training with data editing
Co-training is one of the major semi-supervised learning paradigms that iteratively trains two
classifiers on two different views, and uses the predictions of either classifier on the …
classifiers on two different views, and uses the predictions of either classifier on the …
[PDF][PDF] ECML-PKDD discovery challenge 2006 overview
S Bickel - ECML-PKDD Discovery Challenge Workshop, 2006 - cms.waikato.ac.nz
The Discovery Challenge 2006 deals with personalized spam filtering and generalization
across related learning tasks. In this overview of the challenge we motivate and describe the …
across related learning tasks. In this overview of the challenge we motivate and describe the …
[PDF][PDF] Training spamassassin with active semi-supervised learning
Most spam filters include some automatic pattern classifiers based on machine learning and
pattern recognition techniques. Such classifiers often require a large training set of labeled …
pattern recognition techniques. Such classifiers often require a large training set of labeled …
Ternary reversible extreme learning machines: the incremental tri-training method for semi-supervised classification
XL Tang, M Han - Knowledge and information systems, 2010 - Springer
Tri-training method proposed by Zhou et al., is an excellent method for semi-supervised
classification; nevertheless, the heavy computational burden caused by the retraining …
classification; nevertheless, the heavy computational burden caused by the retraining …
Semi-supervised Bayesian artmap
X Tang, M Han - Applied Intelligence, 2010 - Springer
This paper proposes a semi-supervised Bayesian ARTMAP (SSBA) which integrates the
advantages of both Bayesian ARTMAP (BA) and Expectation Maximization (EM) algorithm …
advantages of both Bayesian ARTMAP (BA) and Expectation Maximization (EM) algorithm …
[PDF][PDF] 基于样本条件价值改进的Co-training 算法
程圣军, 刘家锋, 黄庆成, 唐降龙 - 自动化学报, 2013 - aas.net.cn
摘要Co-training 是一种主流的半监督学习算法. 该算法中两视图下的分类器通过迭代的方式,
互为对方从无标记样本集中挑选新增样本, 以更新对方训练集. Co-training 以分类器的后验概率 …
互为对方从无标记样本集中挑选新增样本, 以更新对方训练集. Co-training 以分类器的后验概率 …
Supervised selective combining pattern recognition modalities and its application to signature verification by fusing on-line and off-line kernels
A Tatarchuk, V Sulimova, D Windridge, V Mottl… - … Classifier Systems: 8th …, 2009 - Springer
We consider the problem of multi-modal pattern recognition under the assumption that a
kernel-based approach is applicable within each particular modality. The Cartesian product …
kernel-based approach is applicable within each particular modality. The Cartesian product …