Assignment  #6
 CSE P573 Autumn 2004 - Applications of AI
Due: Nov 15

Readings for this homework: R&N Chapter 14

Exercises:

Turn in hardcopy in class.  Written exercises should be typed or neatly handwritten.  R&N = Russell & Norvig, Artificial Intelligence, A Modern Approach, 2nd Ed.  Please feel free to talk to other students in the class and to the instructor and TA, but please do not simply copy the solutions from ones you find on the web.

  1. R&N exercise 14.8.  Note that there is a large hint about how to solve this problem on slide #72 of the revised-rn-bayes-all.pdf lecture notes on the course web page.
  2. Read Chapter 15 up through 15.5 as noted below.  Write short (1 or 2 sentence) answers to each of the following questions, to summarize the material.  (You are not expected to understand the details of the material at this point, the purpose of this exercise is to encourage you to read in enough detail to grasp the basic concepts.)
    1. What is the Markov assumption?
    2. What is difference between filtering and smoothing?
    3. Is finding the most likely sequence of states the same as finding the sequence of most likely states?
    4. Is a Kalman filter appropriate for discrete or for continuous variables?
    5. What is the main advantage of an using an HMM (hidden Markov model) over using a DBN (Dynamic Bayesian Network)?
    6. What is the main advantage of using a DBN over an HMM?
    7. What is a "particle" as used in particle filtering algorithms?

Readings for next week (Robotics & Probabilistic Reasoning over Time):