You are on page 1of 21

Applied Probability Lecture 4

Tina Kapur tkapur@ai.mit.edu

Objective
Use Probability to create a software solution to a real-world problem.

Objective
Use Probability to create a software solution to a real-world problem.

Timeline/Administrivia
Friday: vocabulary, Matlab Monday: start medical segmentation project Tuesday: complete project Wednesday: 10am exam Lecture: 10am-11am, Lab: 11am-12:30pm Homework (matlab programs):
PS 4: due 10am Monday PS 5: due 12:30pm Tuesday

Vocabulary
Random variable Discrete vs. continuous random variable PDF Uniform PDF Gaussian PDF Bayes rule / Conditional probability Marginal Probability

Random Variable

Random Variable
Function defined on the domain of an experiment

Example r.v.
Experiment: 2 coin tosses
Sample space: Random variable:

Example r.v.
Experiment: 2 coin tosses
Sample space: HH, HT, TT, TH Random variable: h number of heads in run

Discrete vs. Continuous R. V.

Discrete vs. Continuous R. V.


Domain

PDF

PDF
Function that associates probability values with events in sample space.

PDF
Function that associates probability values with events in sample space. Two characteristics of a PDF:

PDF
Function that associates probability values with events in sample space. Two characteristics of a PDF:
Mean or Expected value Variance

Uniform PDF

Uniform PDF
p(x)

? 0 a x

E(x) = s2(x) =

Gaussian PDF

Gaussian PDF
( x )2 2s 2

1 P( x) e 2 s

mean var iance s 2

Bayes Rule Revisited


P( A | B) P( B | A) P( A) P( B)
P( i | x) P( x | i ) P(i ) P( x)

P( x) P ( x | i ) P (i )
i

P(i | x)

P( x | i ) P(i ) P( x) P( x | i ) P(i ) P( x | i ) P(i )


i

Recitation/Lab
Install Matlab Start Problem Set 1

You might also like