4.6 Review

GAME: GAussian Mixture Error-based meta-learning architecture

期刊

NEURAL COMPUTING & APPLICATIONS
卷 -, 期 -, 页码 -

出版社

SPRINGER LONDON LTD
DOI: 10.1007/s00521-023-08843-z

关键词

Gaussian mixture model; Meta-learning; Noise modeling; Penalized likelihood

向作者/读者索取更多资源

This paper proposes a robust noise model that incorporates a mixture of Gaussian noise modeling strategy into a baseline classification model. The number of mixture components is automatically selected using the penalized likelihood method. The proposed model defines hyperparameters from the error representation and achieves the best performance compared to conventional classification methods.
In supervised learning, the gap between the truth label and the model output is always portrayed by an error function, and a fixed error function corresponds to a specific noise distribution that provides for model optimization. However, the actual noise usually has a much more complex structure. To be better fit for it, in this paper, we propose a robust noise model that embeds a mixture of Gaussian (MoG) noise modeling strategy into a baseline classification model, which is selected as the Gaussian mixture model (GMM) here. Further, to facilitate the automatic selection of the number of mixture components, we apply the penalized likelihood method. Then, we utilize an alternative strategy to update the parameters of the noisy model and the basic GMM classifier. From the meta-learning perspective, the proposed model offers a novel approach to defining the hyperparameters from the error representation. Finally, we compare the proposed approach with three conventional and related classification methods on the synthetic, two benchmark handwriting recognition datasets and the Yale Face dataset. In addition, we embed the noise modeling strategy into the semantic segmentation task. The numerical results validate that our approach achieves the best performance and the efficiency of MoG noise modeling.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据