You are on page 1of 2

1. Which of the following is not a bounty descriptor.

(a) Polygonal (b) Gabor Features


(c) Signature (d) Fourier Descriptor
2. Which of the following is a bounty descriptor?
(a) Fourier Descriptor (b) Gabor Features
(c) Wavelets Features (d) Histogram
3. Where does the bayes rule can be used?
(a) Solving Queries (b) Increasing Complexity
(c) Decreasing Complexity (d) Answering a Probabilistic query
4. Which of the following is co-occurrence matrices-based descriptor?
(a) Entropy (b) Uniformity
(c) Element Difference Moment (d) All of the above
5. What type of classifier we get when covariance matrices of all classes are arbitrary?
(a) Linear Classifier (b) Quadratic Classifier
(c) Either 1 or 2 (d) Higher order polynomial classifier
6. What will be the nature of the decision surface when the covariance matrices of different
classes are identical but otherwise arbitrary?
(a) Orthogonal bisector to two surface (b) Not Orthogonal to two surface
(c) Orthogonal to two surface but not bisector (d) Arbitrary
7. Let’s say you want to solve a classification problem with 5 different classes. How many
discriminators function would you train for this purpose?
(a) 1 (b) 5 (c) 3 (d) 2
8. Which of the following distance measure do we use in case of categorical variables in k-NN
(a) Physical Layer Protocol (b) Euclidean Distance
(c) Manhattan Distance (d) None of these

9. Which of the following will be Euclidean distance between the two data point A (1,3)
and B (2,3)?
(a) 1 (b) 2
(c) 5 (d) 8

10. Which of the following will be Manhattan distance between the two data point A(1,3) and
B(2,3)?
(a) 2 (b) 5 (c) 1 (d) 4
11. Deep learning algorithms are _______ more accurate than machine learning algorithms in
image classification
0.37%
0.41%
33%
0.4%

12. Which of the following is/are Limitations of deep learning?


Obtain huge training datasets
Data labeling
None of the above
All of above

13. Which of the following functions can be used as an activation function in the output layer if
we wish to predict the probabilities of n classes (p1, p2..pk) such that the sum of p over all
n equals to1?
ReLu
Softmax
Tanh
Sigmoid
14. Which of the following techniques perform similar operations as a dropout in a
neural network? Boosting
Bagging
Stacking
None of above

15. The number of nodes in the input layer is 10 and the hidden layer is 5. The
maximum number of connections from the input layer to the hidden layer
are__________
more than 50
less than 50
it is an arbitrary value
50

You might also like