EW-CACTUs-MAML: A Robust Metalearning System for Rapid Classification on a Large Number of Tasks. (3rd February 2022)

• Record Type: Journal Article
• Authors: Wang, Wen-Feng; Zhang, Jingjing; An, Peng
• Other Names: Wang Zhijie Academic Editor.
• Is Part Of: Complexity. Volume 2022(2022)
• Publication Date: 2022-02-03
• Subjects: Chaotic behavior in systems -- Periodicals; Complexity (Philosophy) -- Periodicals; 003
• DOI: 10.1155/2022/7330823
• Languages: English
• ISSNs: 1076-2787

Abstract

Abstract : This study aims to develop a robust metalearning system for rapid classification on a large number of tasks. The model-agnostic metalearning (MAML) with the CACTUs method (clustering to automatically construct tasks for unsupervised metalearning) is improved as EW-CACTUs-MAML after integrated with the entropy weight (EW) method. Few-shot mechanisms are introduced in the deep network for efficient learning of a large number of tasks. The process of implementation is theoretically interpreted as "gene intelligence." Validation of EW-CACTUs-MAML on a typical dataset (Omniglot) indicates an accuracy of 97.42%, performing better than CACTUs-MAML (validation accuracy = 97.22%). At the end of this paper, the availability of our thoughts to improve another metalearning system (EW-CACTUs-ProtoNets) is also preliminarily discussed based on a cross-validation on another typical dataset (Miniimagenet).