590NC Presentation List

Week Topic Paper Number(s) Presenter
Jan 22 Introduction to Bayesian nets, HMMs, and LDSs 2,3 (4 recommended) Aaron Shon
Jan 29 Bayesian nets, HMMs, and LDSs (continued) 2,3 (4 recommended) Aaron Shon
Feb 5 Particle filters and applications 6 David Hsu
Feb 12 Hierarchical HMMs and speech recognition 9, 10 Karim Filali
Feb. 19 Monte Carlo HMMs 7 Dave Grimes
Feb. 26 Liquid state machines 11 Seth Bridges
Mar. 5 Transient synchrony in cortical computation 12 (13 as background) Kam Rahimi
Mar. 12 Face recognition 14 Pat Tressel

Location: We meet in Mary Gates 242 every Tuesday from 1:30 to 3:00pm.

List of papers:

    Overview of Learning and Estimation in Dynamical Systems:

  1. Gentle Tutorial on the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. J. Bilmes. ICSI-TR-97-021, 1997.
  2. From hidden Markov models to linear dynamical systems. Thomas P. Minka. MIT Media Lab Technical Report TR-531, July 1999.
  3. Learning dynamic Bayesian networks. Zoubin Ghahramani. In C.L. Giles and M. Gori (eds.), Adaptive Processing of Sequences and Data Structures . Lecture Notes in Artificial Intelligence, 168-197. Berlin: Springer-Verlag, 1997.
  4. A unifying review of linear Gaussian models. Sam Roweis, Zoubin Ghahramani. Neural Computation 11, pp. 305-345, 1999.


    5. Linear dynamical systems
  5. Overview of Kalman filters (on-line chapter from Maybeck's book)


    6. Papers on Specific Topics:

    Particle Filters
  6. Condensation - conditional density propagation for visual tracking
  7. Monte Carlo Hidden Markov Models: Learning Non-Parametric Models of Partially Observable Stochastic Processes
  8. Monte Carlo Hidden Markov Models


    9. Hierarchical HMMs
  9. The Hierarchical Hidden Markov Model: Analysis and Applications
  10. Linear Time Inference in Hierarchical HMMs


    11. Liquid State Machines
  11. Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations (preprint)


    12. Temporal processing in neural circuits
  12. What is a moment? Transient synchrony as a collective mechanism for spatiotemporal integration
  13. What is a moment? "Cortical" sensory integration over a brief interval
  14. Face identification using one spike per neuron: resistance to image degradations
  15. Formation of temporal-feature maps by axonal propagation of synaptic learning
Head back to the 590NC course web page
Comments to: Raj Rao or Aaron Shon