详细信息
文献类型:期刊文献
中文题名:关于稀疏编码在图像处理中的神经动力学分析
英文题名:Nerve dynamics analysis on the sparse coding in image processing
作者:卢颍霞[1];王如彬[1]
机构:[1]上海华东理工大学认知神经动力研究所,上海200237
年份:2018
卷号:37
期号:22
起止页码:17
中文期刊名:振动与冲击
外文期刊名:Journal of Vibration and Shock
收录:CSTPCD;;EI(收录号:20190306397498);Scopus;北大核心:【北大核心2017】;CSCD:【CSCD2017_2018】;
基金:国家自然科学基金重点项目(11232005; 11472104)
语种:中文
中文关键词:稀疏编码;局部竞争;局部突触可塑性;图像重构
外文关键词:Sparse coding;local competition;local synaptic plasticity;image reconstruction
摘要:初级视皮层V1区神经细胞采用稀疏编码的形式来有效表示自然场景,自然场景的稀疏编码模型可以解释V1区神经元的一些生理学性质,但是我们不知道这种编码模型是否可以通过生物学上的局部突触可塑性规则学习得到。由于生物神经网络中存在一种侧抑制现象即局部竞争,我们基于这种现象并利用突触局部可塑性规则建立了一个发放的神经网络动力学模型。对V1区细胞的感受野进行了仿真,同时利用模型得到的稀疏重构系数,对重构残差进行了讨论。研究表明利用稀疏编码可以得到V1区简单细胞的感受野,同时利用自然图像的输入说明了该动力学模型在生理学意义上的合理性。
The sparse coding model for natural scene can explain some physiological properties of neurons in V1, but it is still unknown whether this coding model could be learned according to the biologically local synaptic plasticity rule. Due to the existence of the lateral inhibition phenomenon in the biological neural network, a neural network dynamic model was established based on this phenomenon and using the local synaptic plasticity. The simulation of the receptive field of V1 cells was carried out. At the same time, the reconstructed residuals were discussed by using the sparse reconstruction coefficients obtained by the model. The results show that the susceptibility field of V1 cells can be obtained by using the sparse coding, and the rationality of the kinetic model can be described by the input of natural images.
参考文献:
正在载入数据...
