CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks
Shi, Jing; Xu, Jiaming; Yao, Yiqun; Xu, Bo
Source PublicationNEURAL NETWORKS
2018
Issue1Pages:1-27
AbstractDeep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new concepts efficiently from scarce data. In this paper, we present a memoryaugmented neural network which is motivated by the process of human concept learning. The training procedure, imitating the concept formation course of human, learns how to distinguish samples from different classes and aggregate samples of the same kind. In order to better utilize the advantages originated from the human behavior, we propose a sequential process, during which the
network should decide how to remember each sample at every step. In this sequential process, a stable and interactive memory serves as an important module. We validate our model in some typical one-shot learning tasks and also an exploratory outlier detection problem. In all the experiments, our model gets highly competitive to reach or outperform those strong baselines.
KeywordOne-shot Learning Memory Attention Deep Reinforcement
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/22135
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Recommended Citation
GB/T 7714
Shi, Jing,Xu, Jiaming,Yao, Yiqun,et al. Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks[J]. NEURAL NETWORKS,2018(1):1-27.
APA Shi, Jing,Xu, Jiaming,Yao, Yiqun,&Xu, Bo.(2018).Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks.NEURAL NETWORKS(1),1-27.
MLA Shi, Jing,et al."Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks".NEURAL NETWORKS .1(2018):1-27.
Files in This Item: Download All
File Name/Size DocType Version Access License
2018-Neural Networks(533KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shi, Jing]'s Articles
[Xu, Jiaming]'s Articles
[Yao, Yiqun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shi, Jing]'s Articles
[Xu, Jiaming]'s Articles
[Yao, Yiqun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shi, Jing]'s Articles
[Xu, Jiaming]'s Articles
[Yao, Yiqun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2018-Neural Networks-Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.