BayesNets - Assignment 2 Click to edit Master subtitle...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
Click to edit Master subtitle style 10/25/10 Assignment 2
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10/25/10 Assignment 2 Implement model a bit like Weiss et al. (2002) Goal: infer motion (velocity) of a rigid shape from observations at two instances in time. Assume distinctive features that make it easy to identify the location of the feature at successive times.
Background image of page 2
10/25/10 Assignment 2 Bx : the x displacement of the blue square (= delta x in one unit of time) By : the y displacement of the blue square Rx : the x displacement of the red square Ry : the y displacement of the red square These observations are corrupted by measurement noise. Gaussian, mean zero, std deviation σ D : direction of motion (up, down, left, right)
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10/25/10 Assignment 2: Generative Model Same assumptions for Bx, By. ) , 0 ( ~ | ) , 0 ( ~ | ) , 1 ( ~ | ) , 1 ( ~ | ) , 0 ( ~ | ) , 1 ( ~ | ) , 1 ( ~ | ) , 0 ( ~ | 2 2 2 2 2 2 2 2 σ Gaussian right D Ry Gaussian left D Ry Gaussian down D Ry Gaussian up D Ry Gaussian down D Rx Gaussian left D Rx Gaussian right D Rx Gaussian up D Rx = = - = = = - = = = Rx conditioned on D=up is drawn from a Gaussian
Background image of page 4
10/25/10 Assignment 2 Math ) ( ) | ( ) | ( ) | ( ) | ( ~ ) , , , | ( ) ( ) | , , , ( ~ ) , , , | ( ) ( ) | , , , ( ) ( ) | , , , ( ) , , , | ( ) , , , ( ) ( ) | , , , ( ) , , , | ( D P D By p D Bx p D Ry p D Rx p By Bx Ry Rx D P D P D By Bx Ry Rx p By Bx Ry Rx D P e P e By Bx Ry Rx p D P D By Bx Ry Rx p By Bx Ry Rx D P By Bx Ry Rx P D P D By Bx Ry Rx p By Bx Ry Rx D P e = = Conditional independence
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10/25/10 Assignment 2 Implementation ) ( ) | ( ) | ( ) | ( ) | ( ~ ) , , , | ( D P D By p D Bx p D Ry p D Rx p By Bx Ry Rx D P )... , ; ( 2 d d rx Gaussian σ μ ... ) 2 / ) ( exp( 2 1 2 2 2 π d d d rx - - Quiz: do we need to normalize the Gaussian density function?
Background image of page 6
10/25/10 Assignment 2 Goal You will explore the role of the priors. The Weiss model showed that priors play an important role when § observations are noisy § observations don’t provide strong constraints § there aren’t many observations.
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10/25/10 Naïve Bayes Classifier Homework 2 asks you to implement a naïve Bayes classifier.
Background image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/24/2010 for the course CSCI 4202 at Colorado.

Page1 / 31

BayesNets - Assignment 2 Click to edit Master subtitle...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online