Reading list

Partial reading list more will follow.¶

Read stared material only when explicitly mentioned, i.e., all means all non-stared.

Fixed partChapter 1: Introduction. All.Chapter 2: Probability. You should know: 2.2, 2.3.1,2.3.2, 2.3.4, 2.4.1, 2.4.4, 2.4.5, 2.5, 2.6.3, 2.7 (understand the ideas), definitions and examples in 2.8.

Chapter 3: Generative models for discrete data. Entire chapter except 3.2 (but if you do not know the definitions from class read those).

Chapter 4: Gaussian models. Only: 4.1-4.1.3, 4.2-4.2.2Chapter 5: Bayesian statistics. All except: 5.3.2.3, (5.4.2 is stared), 5.6 (not yet covered on lectures, but soon).

Chapter 10: Directed graphical models. All except 10.2.4,10.2.5., 10.4, 26.3.1, 26.3.2.¶ Chapter 11: Mixture models the EM algorithm. 11.1, 11.2.1-11.2.3, 11.4-11.4.2.5, 11.4.2.8, 11.4.4, 11.4.7, read also 2.8.1, 2.8.2The following together will additional chapters will probably be the included in the reading list.

Chapter 170: Markov models and hidden Markov models. Read 17.1-17.2 now or later (it is more important for MCMC). Read 17.3- 17.5 and 17.6.6. Gaussian emission distributions are not mandatoryDirected graphical models. All except 10.2.4,10.2.5., 10.4, 26.3.1, 26.3.2.

Chapter 18: SSM 18.1-18.3, but not "Online parameter learning using least squares" and only what the Kalman filter does.

Chapter 19. Undirected graphical models. 19.1-19.3, 19.4.1, 19.4.3.

Chapter 20 Exakt inference for graphical models. Selected parts. 20.1-20.3

Chapter 23: Monte Carlo inference. Selected partsNot 23.2.2, Not 23.6

Chapter 24: Markov Chain Monte Carlo. 24.3.6 is included (although stared)Not 24.2.2, 24.2.5, 24.3.3.1, 24.3.7, 24.4.2., 24.4.4