Kingsley Sage and Hilary Buxton
The preparation of this course was funded by ECVision under Specific Action 8-3
Course Outline
Lecture 2: Generative and discriminative models Lecture 3: Graphical models / what are they? Lecture 4: Graphical models / Examples of different sorts and "family of models" Lecture 5: Probability thoery reminder, Bayes rule and Bayesian networks Lecture 6: Inference in Bayesian networks Lecture 7: Discrete HMMs Lecture 8: Gaussian Mixtures and continuous valued HMMs Lecture 9: Behaviour recognition: Bottom up/top-down vision. HIVIS, DBNs and DDNs, BAT Lecture 10: Visual task control: ActIPret Lecture 11: Learning in HMMs (discrete case) Lecture 12: Learning in HMM (continuous case) & stochastic sampling Lecture 13: Learning in BBNs, taxonomy of learning methods and 1 method in detail (full observability and known structure) Lecture 14: Learning in BBNs, overview of other 3 methods Lecture 15: Active cameras, Bayes Nets and tasks - future challenges The complete course is available for download in a zip file (215 Mb) Individual lectures can also be viewed on-line or downloaded in zip files.
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Site generated on Friday, 06 January 2006
|