A Novel Biologically Inspired Hierarchical Model for Image Recommendation
Lu Yanfeng(吕彦锋)1; Qiao Hong2,3; Li Yi4; Jia Lihao1; Zhang Aixuan1,5
2017
会议名称International Symposium on Neural Networks 2017
会议日期2017.6.20--2017.6.26
会议地点Sapporo, Japan
摘要The biologically inspired model (BIM) for invariant feature representation has attracted widespread attention recently, which approximately follows the organization of cortex visuel. BIM is a computational architecture with four layers. With the image data size increases, the four-layer framework is prone to be overfitting, which limits its application. To address this issue, motivated by biology, we propose a biologically inspired hierarchical model (BIHM) for image feature representation, which adds two more discriminative layers upon the conventional four-layer framework. In contrast to the conventional BIM that mimics the inferior temporal cortex, which corresponds to the low level feature invariance and selectivity, the proposed BIHM adds two more layers upon the conventional BIM framework to simulate inferotemporal cortex, exploring higher level feature invariance and selectivity. Furthermore, we firstly utilize the BIHM in the image recommendation. To demonstrate the effectiveness of proposed model, we use it in image recommendation task and perform experiment on CalTech5 datasets. The experiment results show that BIHM exhibits higher performance than conventional BIM and is very comparable to existing architectures.
关键词Visual Cortex Biologically Inspired Model Classification Image Recommendation.
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/15337
专题复杂系统管理与控制国家重点实验室_机器人理论与应用
作者单位1.Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences
2.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences
3.CAS Center for Excellence in Brain Science and Intelligence Technology
4.School of Information Engineering, Nanchang University
5.School of Mechanical and Material Engineering, North China University of Technology
推荐引用方式
GB/T 7714
Lu Yanfeng,Qiao Hong,Li Yi,et al. A Novel Biologically Inspired Hierarchical Model for Image Recommendation[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A Novel Biologically(546KB)会议论文 开放获取CC BY-NC-SA浏览 下载
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
[Lu Yanfeng(吕彦锋)]的文章
[Qiao Hong]的文章
[Li Yi]的文章
百度学术
百度学术中相似的文章
[Lu Yanfeng(吕彦锋)]的文章
[Qiao Hong]的文章
[Li Yi]的文章
必应学术
必应学术中相似的文章
[Lu Yanfeng(吕彦锋)]的文章
[Qiao Hong]的文章
[Li Yi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: A Novel Biologically Inspired Hierarchical Model for Image Recommendation.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。