CASIA OpenIR  > 类脑智能研究中心
End-to-End Lifelong Learning: a Framework to Achieve Plasticities of both the Feature and Classifier Constructions
Hao, Wangli1; Fan, Junsong1; Zhang, Zhaoxiang1,2,3; Zhu, Guibo1
Source PublicationCOGNITIVE COMPUTATION
2018-04-01
Volume10Issue:2Pages:321-333
SubtypeArticle
Abstract

Plasticity in our brain offers us promising ability to learn and know the world. Although great successes have been achieved in many fields, few bio-inspired machine learning methods have mimicked this ability. Consequently, when meeting large-scale or time-varying data, these bio-inspired methods are infeasible, due to the reasons that they lack plasticity and need all training data loaded into memory. Furthermore, even the popular deep convolutional neural network (CNN) models have relatively fixed structures and cannot process time varying data well. Through incremental methodologies, this paper aims at exploring an end-to-end lifelong learning framework to achieve plasticities of both the feature and classifier constructions. The proposed model mainly comprises of three parts: Gabor filters followed by max pooling layer offering shift and scale tolerance to input samples, incremental unsupervised feature extraction, and incremental SVM trying to achieve plasticities of both the feature learning and classifier construction. Different from CNN, plasticity in our model has no back propogation (BP) process and does not need huge parameters. Our incremental models, including IncPCANet and IncKmeansNet, have achieved better results than PCANet and KmeansNet on minist and Caltech101 datasets respectively. Meanwhile, IncPCANet and IncKmeansNet show promising plasticity of feature extraction and classifier construction when the distribution of data changes. Lots of experiments have validated the performance of our model and verified a physiological hypothesis that plasticity exists in high level layer better than that in low level layer.

KeywordPlasticity Lifelong Learning End-to-end Incremental Pcanet Incremental Kmeansnet Incremental Svm
WOS HeadingsScience & Technology ; Technology ; Life Sciences & Biomedicine
DOI10.1007/s12559-017-9514-0
WOS KeywordOBJECT RECOGNITION ; COMPONENT ANALYSIS ; VISUAL-SYSTEM ; EIGENFACES ; NETWORKS ; MODEL
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61773375 ; Microsoft Collaborative Research Project ; 61375036 ; 61511130079)
WOS Research AreaComputer Science ; Neurosciences & Neurology
WOS SubjectComputer Science, Artificial Intelligence ; Neurosciences
WOS IDWOS:000430190600012
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20440
Collection类脑智能研究中心
Affiliation1.UCAS, Inst Automat, Beijing, Peoples R China
2.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China
3.Chinese Acad Sci, CASIA, Inst Automat, Beijing, Peoples R China
Recommended Citation
GB/T 7714
Hao, Wangli,Fan, Junsong,Zhang, Zhaoxiang,et al. End-to-End Lifelong Learning: a Framework to Achieve Plasticities of both the Feature and Classifier Constructions[J]. COGNITIVE COMPUTATION,2018,10(2):321-333.
APA Hao, Wangli,Fan, Junsong,Zhang, Zhaoxiang,&Zhu, Guibo.(2018).End-to-End Lifelong Learning: a Framework to Achieve Plasticities of both the Feature and Classifier Constructions.COGNITIVE COMPUTATION,10(2),321-333.
MLA Hao, Wangli,et al."End-to-End Lifelong Learning: a Framework to Achieve Plasticities of both the Feature and Classifier Constructions".COGNITIVE COMPUTATION 10.2(2018):321-333.
Files in This Item: Download All
File Name/Size DocType Version Access License
End-to-End Lifelong (1189KB)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
[Hao, Wangli]'s Articles
[Fan, Junsong]'s Articles
[Zhang, Zhaoxiang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hao, Wangli]'s Articles
[Fan, Junsong]'s Articles
[Zhang, Zhaoxiang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hao, Wangli]'s Articles
[Fan, Junsong]'s Articles
[Zhang, Zhaoxiang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: End-to-End Lifelong Learning a Framework to Achieve Plasticities of both the Feature and Classifier Constructions.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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