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
Conference NameThe 2015 International Joint Conference on Neural Networks (IJCNN 2015)
Source PublicationProceedings of the 2015 International Joint Conference on Neural Networks (IJCNN 2015)
Conference DateJuly 12-17, 2015
Conference PlaceKillarney, Ireland
AbstractEarly 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.
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/10360
Collection类脑智能研究中心
AffiliationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
HEVS_ A Hierarchical(2089KB)会议论文 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
[Jiuqi Han(韩久琦)]'s Articles
[Qingqun Kong(孔庆群)]'s Articles
[Yi Zeng(曾毅)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jiuqi Han(韩久琦)]'s Articles
[Qingqun Kong(孔庆群)]'s Articles
[Yi Zeng(曾毅)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jiuqi Han(韩久琦)]'s Articles
[Qingqun Kong(孔庆群)]'s Articles
[Yi Zeng(曾毅)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: HEVS_ A Hierarchical Computational Model for Early Stages of the Visual System.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

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