Scribd
Upload
4 views10 pages

AIML ML Session 16

Uploaded by

chirag
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
4 views10 pages

AIML ML Session 16

Uploaded by

chirag
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Worked Out Problems

Dr. Sugata Ghosal


CSIS Off-Campus Faculty
BITS Pilani
K-Means
Assume that a number of points are distributed along the x-axis:
and an outlier point
We would like to use the -Means algorithm to find two clusters for these points. Initially, one
cluster center is chosen to be . Where should the other cluster center be placed on the x-axis
initially so that one of the clusters formed has all the given data points and the other cluster
has none? What will be the final locations of the cluster centers?
EM Maximization
Suppose we have the following one-dimensional data at -4.0, -.3.0, -2.0, -1.0, 0.0, 1.0,
2.0, 3.0, 4.0. Use the EM algorithm to find a Gaussian mixture model consisting of
exactly one Gaussian that fits the data. Assume that the initial mean of the Gaussian
is 10.0 and the initial variance is 1.0.
AdaBoost
Consider training an AdaBoost classifier using decision stumps on the following
data set. Decision stump classifier chooses a constant value c and classifies all
points where x > c as one class and other points where x ≤ c as the other class.

1. What is the initial weight that is assigned to each data point?

2. Show the decision boundary for the first decision stump.

3. Calculate the importance of the first decision stump.

4. Calculate the weights for the next iteration increases in the boosting process
Bayesian Learning
A dataset consists of the results of 100 independent coin tosses of the same coin where
30 turn out to be heads and 70 turn out to be tails. Let be the probability of tossing a head.
How many datasets on 100 coin tosses are possible which have the same likelihood as the
given dataset ? Determine the maximum likelihood estimate of the parameter using
appropriate calculations.
Bayesian Learning
Let be two real-valued features and be a Boolean-valued function of the given features
such that the Gaussian Naïve-Bayes assumptions are satisfied. Suppose
.
Assume that and and Calculate the standard deviations and and the probability
Bayesian Learning
Bayesian Learning
Let say we have a dice of 4 sides. Where { (x,P(x)) : (0,a), (1,(1-a)/3), (2,(1-a)/2),
(3,(1-a)/6) }. If the tossing event is observed as (0,1,2,3,2,3,1,0) then what is the
most probable value of a ?
SVM
Solve the below and find the equation for hyper plane using linear Support Vector Machine
method. Positive Points: {(3, 2), (4, 3), (2, 3), (3, -1)} Negative Points: {(1, 0), (-1, -1), (0, 2),
(-1, 2)}. Find the support vectors. Determine the equation of hyperplane if it is changed and
give a reason if it is not changed for the following two cases
• If the point (2, 3) is removed. If the point (5,4) is added

(2,3) (4,3)

(-1,2) (0,2)

(3,2)

(1,0)

(-1,-1)

(3,-1)
SVM

Find the maximum margin decision boundary.

You might also like