CS379C: Computational Models of the Neocortex

Spring 2010

Calendar of Invited Talks and Student Presentations:

  • March 29: Lecture: Introduction to Computational Models of Necortex (PDF)

  • March 31: Lecture: Basic Molecular Neuroscience: Action Potentials (PDF)

  • April 5: Lecture: Basic Molecular Neuroscience: Synaptic Transmission (PDF)

  • April 7: Lecture: Basic Molecular Neuroscience: Development and Memory (PDF)

  • April 12: Lecture: Biology and Computation in the Primate Visual System (PDF)

  • April 14: Dick Lyon will discuss models of hearing in mammals, mostly sub-cortical, that lead to the cortex receiving auditory images as input, so that primary auditory area A1 can function analogously to the way that V1 does for visual images. Read pages 344–375 in Neuroscience: Exploring the Brain [1].

  • April 19: Zhenghao Chen will be presenting A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation [10] (HTML)

  • April 21: Nicholas Henderson will be presenting Visual Features of Intermediate Complexity and their use in Classification [18] (PDF) and Computation of pattern invariance in brain-like structures [17] (PDF)

  • April 26: Brad Busse will be presenting Representation of the spatial relationship among object parts by neurons in macaque inferotemporal cortex [19] (PDF)

  • April 28: Pang Wei Koh will be presenting Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations [6] (PDF) and Sparse deep belief net model for visual area V2 [5] (PDF)

  • May 3: Kevin Leung and Ben Varkey Benjamin will be presenting A neurobiological model of visual attention and pattern recognition based on dynamic routing of information [8] (PDF) and Processing Shape, Motion and Three-dimensional Shape-from-motion in the Human Cortex [7] (HTML)

  • May 5: Bruno Olshausen will be talking about surface perception, the problem of occlusion, and aspects of “what we know and don’t know” about visual system function. Read How close are we to understanding V1? [9] (PDF)

  • May 10: Dan Robinson and Konstantinos Katsiapis will be presenting Recovering Surface Layout from an Image [4] (PDF) and Decomposing a scene into geometric and semantically consistent regions [3] (PDF)

  • May 12: Dileep George will be talking about his work with Jeff Hawkins on Hierarchical Temporal Memory. Read Towards a mathematical theory of cortical micro-circuits [2] (HTML)

  • May 17: David Brody and Marvin Liu Shu will be collaborating to present two papers: A Neural Model of how Horizontal and Interlaminar connections of Visual Cortex Develop into Adult Circuits that Carry Out Perceptual Grouping and Learning.  (PDF) and The Division of Labor Between the Neocortex and Hippocampus.  (PDF)

  • May 19: Brian Wandell will be talking about a computational project simulating retinal ganglion cells to understand the information present in different types of circuits. The project involves large-scale modeling of neural circuits and connecting this modeling with human performance. Reading TBD.

  • May 24: David Kamm and Jaehyun Park will be collaborating to present two papers: Hierarchical models of object recognition in cortex [11] (PDF) and Object Recognition with Cortex-like Mechanisms [12] (HTML)

  • May 26: Anish Mitra and Thatcher Michael Kimball (pending confirmation) will be presenting Face Recognition by Humans; Nineteen Results All Computer Vision Researchers Should Know About [13] (PDF) and Visual Object Recognition: Can a Single Mechanism Suffice? [16] (PDF)

  • May 31: Memorial Day.

  • June 2: TBD


  • References

    [1]   Mark F. Bear, Barry Connors, and Michael Paradiso. Neuroscience: Exploring the Brain (Third Edition). Lippincott Williams & Wilkins, Baltimore, Maryland, 2006.

    [2]   Dileep George and Jeff Hawkins. Towards a mathematical theory of cortical micro-circuits. PLoS Computational Biology, 5(10), 2009.

    [3]   Stephen Gould, Tianshi Gao, and Daphne Koller. Region-based segmentation and object detection. In Y. Bengio, D. Schuurmans, J. Lafferty, C. K. I. Williams, and A. Culotta, editors, Advances in Neural Information Processing Systems 22, pages 655–663. MIT Press, Cambridge, MA, 2009.

    [4]   Derek Hoiem, Alexei Efros, and Martial Hebert. Recovering surface layout from an image. International Journal of Computer Vision, 75(1):151–172, 2007.

    [5]   Honglak Lee, Chaitanya Ekanadham, and Andrew Ng. Sparse deep belief net model for visual area V2. In J.C. Platt, D. Koller, Y. Singer, and S. Roweis, editors, Advances in Neural Information Processing Systems 20, pages 873–880. MIT Press, Cambridge, MA, 2008.

    [6]   Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In ICML ’09: Proceedings of the 26th Annual International Conference on Machine Learning, pages 609–616, New York, NY, 2009. ACM.

    [7]   Scott O. Murray, Bruno A. Olshausen, and David L. Woods. Processing shape, motion and three-dimensional shape-from-motion in the human cortex. Cerebral Cortex, 13(5):508–516, 2003.

    [8]   B. A. Olshausen, A. Anderson, and D. C. Van Essen. A neurobiological model of visual attention and pattern recognition based on dynamic routing of information. Journal of Neuroscience, 13(11):4700–4719, 1993.

    [9]   B. A. Olshausen and D. J. Field. How close are we to understanding V1? Neural Computation, 17:1665–1699, 2005.

    [10]   Nicolas Pinto, David Doukhan, James DiCarlo, and David Cox. A high-throughput screening approach to discovering good forms of biologically inspired visual representation. PLoS Computational Biology, 5(11):e1000579, November 2009.

    [11]   M. Riesenhuber and T. Poggio. Hierarchical models of object recognition in cortex. Nature Neuroscience, 2(11):1019–1025, November 1999.

    [12]   T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio. Object recognition with cortex-like mechanisms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(3):411–426, 2007.

    [13]   Pawan Sinha, Benjamin Balas, Yuri Ostrovsky, and Richard Russell. Face recognition by humans; nineteen results all computer vision researchers should know about. Proceedings of the IEEE, 94(11):1948–1962, 2006.

    [14]   Erik Sudderth and Michael Jordan. Shared segmentation of natural scenes using dependent Pitman-Yor processes. In D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, editors, Advances in Neural Information Processing Systems 21, pages 1585–1592. MIT Press, 2009.

    [15]   Erik B. Sudderth, Antonio Torralba, William T. Freeman, and Alan S. Willsky. Describing visual scenes using transformed objects and parts. International Journal of Computer Vision, 77(1-3):291–330, 2008.

    [16]   M. J. Tarr. Visual object recognition: Can a single mechanism suffice? In M. A. Peterson and G. Rhodes, editors, Perception of Faces, Objects, and Scenes: Analytic and Holistic Processes, pages 177–211. Oxford University Press, Oxford, UK, 2003.

    [17]   S. Ullman and S. Soloviev. Computation of pattern invariance in brain-like structures. Neural Networks, 12:1021–1036, 1999.

    [18]   Shimon Ullman, Michel Vidal-Naquet, and Erez Sali. Visual features of intermediate complexity and their use in classification. Nature Neuroscience, 5(7):682–687, 2002.

    [19]   Y. Yamane, K. Tsunoda, M. Matsumoto, N. A. Phillips, and M. Tanifuji. Representation of the spatial relationship among object parts by neurons in macaque inferotemporal cortex. Journal Neurophysiology, 96:3147–3156, 2006.