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
2018-04-01
发表期刊COGNITIVE COMPUTATION
卷号10期号:2页码:321-333
文章类型Article
摘要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.
关键词Plasticity Lifelong Learning End-to-end Incremental Pcanet Incremental Kmeansnet Incremental Svm
WOS标题词Science & Technology ; Technology ; Life Sciences & Biomedicine
DOI10.1007/s12559-017-9514-0
关键词[WOS]OBJECT RECOGNITION ; COMPONENT ANALYSIS ; VISUAL-SYSTEM ; EIGENFACES ; NETWORKS ; MODEL
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China(61773375 ; Microsoft Collaborative Research Project ; 61375036 ; 61511130079)
WOS研究方向Computer Science ; Neurosciences & Neurology
WOS类目Computer Science, Artificial Intelligence ; Neurosciences
WOS记录号WOS:000430190600012
引用统计
被引频次:1[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/20440
专题类脑智能研究中心
作者单位1.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
推荐引用方式
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.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
End-to-End Lifelong (1189KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Hao, Wangli]的文章
[Fan, Junsong]的文章
[Zhang, Zhaoxiang]的文章
百度学术
百度学术中相似的文章
[Hao, Wangli]的文章
[Fan, Junsong]的文章
[Zhang, Zhaoxiang]的文章
必应学术
必应学术中相似的文章
[Hao, Wangli]的文章
[Fan, Junsong]的文章
[Zhang, Zhaoxiang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: End-to-End Lifelong Learning a Framework to Achieve Plasticities of both the Feature and Classifier Constructions.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。