CASIA OpenIR  > 类脑智能研究中心
HEVS: A Hierarchical Computational Model for Early Stages of the Visual System
Jiuqi Han(韩久琦); Qingqun Kong(孔庆群); Yi Zeng(曾毅); Hongwei Hao(郝红卫)
2015
会议名称The 2015 International Joint Conference on Neural Networks (IJCNN 2015)
会议录名称Proceedings of the 2015 International Joint Conference on Neural Networks (IJCNN 2015)
会议日期July 12-17, 2015
会议地点Killarney, Ireland
摘要Early stages of the human visual system consist of retinal cones, retinal ganglion cells(RGC), lateral geniculate nucleus(LGN) and V1. Modeling early visual stages is conducive to reveal the mechanism of visual signal preprocessing and representation inside brain, as well as settle challenges artificial intelligence confronts. However, a majority of previous work often models RGC/LGN or V1 separately, seldom modeling them together hierarchically. In order to be consistent with the biological results, we propose HEVS (a Hierarchical computational model for Early stages of the Visual System), a feedforward neural network composed of three layers, which represent receptor neurons, RGC/LGN and V1 successively. Exactly as the visual system, the proposed locally connected model is derived in the unsupervised scenario on natural images and trained in the bottom-up order. In order to learn the two connection weights among three layers, we formulate two optimization problems based on the reconstruction error and sparse learning. Unlike traditional models on RGC/LGN, we perform weighted similarity measuring as a regular term to simulate the strong correlations among nearby neuron spikes in the same stage. Different from existing researches on modeling V1 neurons from image pixels directly, we transmit the signals represented by the ganglion cells in the second layer to the V1 neurons in the third layer. Moreover, solutions to these objectives are provided as well. Experimental results demonstrate that the characteristics of HEVS are consistent with those of the corresponding biological stages. The results further verify the performance of HEVS on dealing with the de-blurring and de-noising tasks.
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/10360
专题类脑智能研究中心
作者单位Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Jiuqi Han,Qingqun Kong,Yi Zeng,et al. HEVS: A Hierarchical Computational Model for Early Stages of the Visual System[C],2015.
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
HEVS_ A Hierarchical(2089KB)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
[Jiuqi Han(韩久琦)]的文章
[Qingqun Kong(孔庆群)]的文章
[Yi Zeng(曾毅)]的文章
百度学术
百度学术中相似的文章
[Jiuqi Han(韩久琦)]的文章
[Qingqun Kong(孔庆群)]的文章
[Yi Zeng(曾毅)]的文章
必应学术
必应学术中相似的文章
[Jiuqi Han(韩久琦)]的文章
[Qingqun Kong(孔庆群)]的文章
[Yi Zeng(曾毅)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: HEVS_ A Hierarchical Computational Model for Early Stages of the Visual System.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。