# Machine Learning and Deep Learning – Fundamentals and Applications | Week 1

Session: JULY-DEC 2024

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

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

Q1. In a binary classification problem, the confusion matrix is a __ matrix.
1×1
2×2
3×3
1×2

Q2. Precision is defined as
TP / (TP + TN)
TP / (TP + FN)
TP / (TP + FP)
TN / (TN + FP)

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

Q3. In a binary classification problem, a classifier correctly predicts 90 instances as positive, incorrectly predicts 15 instances as positive when they are negative, correctly predicts 90 instances as negative, and incorrectly predicts 10 instances as negative when they are positive. What is the accuracy of the classifier?
80
85
87.8
95

Q4. For the above question find the F1 score?
78.2%
85%
87.8%
90.2%

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

Q5. Consider a dataset with actual values (Y) and predicted values (Y_pred) given below:
Y = [5, 8, 12, 10, 15],
Y_pred = [4, 7, 10, 11, 13].
What is the bias of the model?

0
-1
2.2
None of the above

Q6. What is the variance of the model for the data given in the above question?
0
-1
2.2
None of the above

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

Q7. Given X = {-2, -1, 0, 1, 2, 3, 4, 5, 6, 7} and the corresponding Y = {-0.5267, 1.3517, 3.8308, 5.5853, 7.5497, 9.9172, 11.2858, 13.7572, 15.7537, 17.3804}. Find the parameters of the linear regression model.
2.0065, 4.0312
2.0065, 3.5722
1.9214, 3.5722
None of the above

Q8. Find the MSE for the above question.
0.05783
0.04247
0.04876
None of the above

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

Q9. A model with high variance and low bias means
It can be too simple to understand the patterns of the data used in the training.
An excellent performance in the training data, but has a significant decrease in performance when evaluating the test data.
The model fits the test data better.
The model becomes less sensitive to the training data.

Q10. Which of the following techniques is used to prevent overfitting in machine learning?
To create complex machine learning models.
Train the model for more epochs.
Using a regularization to the model.
To increase the variance of the model.