题目:Sparse representation in computer vision and visual cortex 主讲人: 彭义刚,博士毕业于清华大学自动化系,研究方向为image/video processing, sparse representation, low-rank matrix recovery。 肖达,北京邮电大学计算机学院教师。 提纲: 1. From sparsity to low-rankness and more(讲稿下载: http://vdisk.weibo.com/s/KMQW6 ) 2. Self-organizing cortical map model and Topographica simulator(讲稿下载: http://vdisk.weibo.com/s/KMR4I 。另见参考文献) 视频回放: http://www.duobei.com/room/4411032613 参考文献: . Bednar JA: Building a mechanistic model of the development and function of the primary visual cortex. J Physiol Paris, 2012, 106(5-6):194-211. .Demo代码网址 http://topographica.org/
题目:Descriptive, Mechanistic and Interpretive Models of Primary Visual Cortex 主讲人:肖达,北京邮电大学计算机学院教师。 袁行远,前淘宝网数据挖掘与并行计算高级算法工程师,现辞职休假中。 提纲: 1.Descriptive models (What): * Responses of a Neuron in an Intact Cat Brain, (视频: Hubel Wiesel - Cortical Neuron - V1 http://v.youku.com/v_show/id_XNDc0MTkxODc2.html ) * Contrast sensitivity of Human * Receptive Fields and Edges Detection Program Demo 2.Machanistic Models (How): * Oriented Receptive Fields and Position-Less Receptive Fields * Fourier Decomposition hypothesis * Build Self-Organizing Map for V1 3.Interpretive Models (Why): * What is the Best Multi-Stage Architecture for Object Recognition 4.The columnar organization of the neocortex and its implication for computer vision 参考文献: 【NB】Matteo Carandini (2012) Area V1. Scholarpedia, 7(7):12105. http://www.scholarpedia.org/article/Area_V1 【NB】【CM】Carandini M, et al. (2005) Do we know what the early visual system does? Journal of Neuroscience, 25:10577-10597. 【NB】Douglas, RJ and Martin, KAC (2007) Recurrent neuronal circuits in the neocortex. Current Opinion in Biology, 17:496-500. 【NB】Douglas, RJ and Martin, KAC (2010) Canonical cortical circuits. Chapter 2 in Handbook of Brain Microcircuits 15-21. 【ML】Kevin Jarrett, Koray Kavukcuoglu, Marc’Aurelio Ranzato, and Yann LeCun. (2009) What is the Best Multi-Stage Architecture for Object Recognition? in Proc. International Conference on Computer Vision (ICCV’09). (文章前的标签代表类型,NB=神经生物学发现,CM=计算模型,ML=机器学习算法,SP=统计物理。) 多贝视频: http://www.duobei.com/room/3011311368 讲稿: 袁行远,What do we know about V1 http://vdisk.weibo.com/s/u4Vws15JLvz_z 代码演示网址 http://www.demogng.de/ 肖达,Modular organization of neocortex and its implication for computer vision http://vdisk.weibo.com/s/u4Vws15JLvz_l