# ML Deep Learning Fundamentals Applications Week 2 Answers

Are you searching for reliable ML Deep Learning Fundamentals Applications Week 2 Answers 2024? Look no further! Our solutions are designed to provide clear, detailed answers, helping you navigate your NPTEL course with confidence.

Course Name: Machine Learning and Deep Learning – Fundamentals and Applications

## ML Deep Learning Fundamentals Applications Week 2 Answers (July-Dec 2024)

Q1.Consider a binary classification problem with two classes, A and B with prior probability P(A)=0.6
and P(B)=0.4 .Let X be a single binary feature that can take values 0 or 1 .Given: P(X=1|A)=0.8
and P(X=0|B)=0.7.Determine which class the classifier will classify when X=1

Class A
Class B
Equiprobable for Class A and Class B
Not enough information

Q2. Consider the following Bayesian network, where F = having the flu and C = coughing:

0.23
0.03
0.35
None of the above.

These are ML Deep Learning Fundamentals Applications Week 2 Answers

Q3. For the above question, Are C and F independent in the given Bayesian network?
Yes.
No.
Can’t say.
Insufficient information.

Q4. Bayes’ decision theory assumes that:
The feature vectors are dependent on each other.
The feature vectors are normally distributed.
The feature vectors are identically distributed.
The feature vectors are uniformly distributed.

Answer: The feature vectors are identically distributed.

These are ML Deep Learning Fundamentals Applications Week 2 Answers

Q5. Assume that the word ‘offer’ occurs in 80% of the spam messages in my account. Also, let’s assume ‘offer’ occurs in 10% of my desired e-mails. If 30% of the received e-mails are considered as a scam, and I will receive a new message which contains ‘offer’, what is the probability that it is spam?
0.778
0.774
0.668
0.664

Q6. The optimal decision in Bayes Decision Theory is the one that

Minimizes the error rate.
Maximizes the error rate.
Minimizes the loss function.
Maximizes the loss function.

Q7. The risk function in Bayesian decision theory combines:
The prior probabilities and the likelihood function.
The decision boundaries and the feature vectors.
The training set and the test set.
The loss function and the decision rule

Answer: The loss function and the decision rule

Q8. The loss function used in risk-based Bayesian decision theory:
Quantifies the cost of different types of errors.
Is equal to the likelihood function.
Ignores the prior probabilities of the classes.
Is not used in the decision-making process

Answer: Quantifies the cost of different types of errors.

These are Machine Learning and Deep Learning Fundamentals and Applications Week 1 Nptel Assignment Answers

Q9. The risk-based Bayesian decision rule accounts for the consequences of different decisions by considering the:
Number of features in the dataset
The complexity of the classifier
Uncertainty in the data and the associated losses
Mean and standard deviation of the feature vectors

Answer: Uncertainty in the data and the associated losses

Q10. The generalized form of a Bayesian network that represents and solves decision problems under uncertain knowledge is known as an?
Directed Acyclic Graph
Table of conditional probabilities
Influence diagram
None of the above