1
发表于 2013-07-21 04:41:14 由 king

脑与deep learning读书会2.Descriptive, Mechanistic and Interpretive Models of Primary Visual Cortex 

录音:http://www.duobei.com/room/3011311368

讲稿:http://vdisk.weibo.com/s/u4Vws15JLvz_z ,http://vdisk.weibo.com/s/u4Vws15JLvz_l

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
   
时间:2013年6月30日下午2点半 
地点:海淀区学清路768创意产业园B座蕴味咖啡(公交“石板房”站,问路电话61199210) 
   
  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。)

2012-2022 www.swarma.org, all rights reserved