[go: up one dir, main page]
Scribd
Upload
405 views4 pages

MCQ

This document contains 14 multiple choice questions about machine learning and deep learning concepts. The questions cover topics such as feature selection, cross-validation, support vector machines, distances, neural network architectures, overfitting, pooling, feature extraction, recurrent neural networks, temporal data modeling, convolutional neural networks, and autoencoders. The correct answers to each question are also provided.

Uploaded by

spraveen2007
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
405 views4 pages

MCQ

This document contains 14 multiple choice questions about machine learning and deep learning concepts. The questions cover topics such as feature selection, cross-validation, support vector machines, distances, neural network architectures, overfitting, pooling, feature extraction, recurrent neural networks, temporal data modeling, convolutional neural networks, and autoencoders. The correct answers to each question are also provided.

Uploaded by

spraveen2007
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 4

1.

Feature selection aims to eliminate features that aren’t necessary

(A) Rich

(B) Redundant

(C) Irrelevant

(D) Relevant

Ans:B

2. In machine learning, LOOCV stands for

(A) Love one-out cross validation

(B) Leave-one-out cross-validation

(C) Leave-object oriented cross-validation

(D) Leave-one-out class-validation

Ans:B

3. Which of the following statements about SVM is correct?

(A) It is useful only in high-dimensional spaces

(B) It always gives an approximate value

(C) It is accurate

(D) Understanding SVM is difficult

Ans:D

4. The Manhattan distance between the two data points A(8,3) and B(4,3) will be which of the
following?

(A) 1

(B) 2

(C) 4
(D) 8

Ans:C

5. How many layers are built in deep learning algorithms?

(A) 1

(B) 2

(C) 4

(D) 3

Ans:D

6. Between the input and output, which neural network has only one hidden layer?

(A) Shallow neural network

(B) Deep neural network

(C) Feed-forward neural network

(D) Recurrent neural network

Ans:A

7. In image classification, deep learning methods are _________ more accurate than
machine learning algorithms.

(A) 33%

(B) 0.37

(C) 0.4

(D) 0.41

Ans:D

8. Which strategy does not prevent a model from overfitting to the training data?

(A)Early stopping
(B)Dropout

(C)Data augmentation

(D)Pooling

Ans:B

9. _________is a pooling process that selects the most significant element from the feature map
region covered by the filter.

A. Max Pooling

B. Average Pooling

C. Global pooling

D. None of these

Ans : A

10. Which of the following is a feature extraction example?

(A) construction bag of words from an email

(B)applying pca to project high dimensional data

(C) removing stop words

(D) forward selection

Ans:B

11. What is the name of the strategy for overcoming the Decay of Information over time in
RNN?
(A)Back Propagation
(B)Gradient Descent
(C)Activation
(D)Gating

Ans:D

12. Which Neural Network Model for Temporal Data is the best?
(A)Recurrent Neural Network
(B)Convolution Neural Networks
(C)Temporal Neural Networks
(D)Multi Layer Perceptrons
Ans:A

13. In a Convolution Neural Network, why is the Pooling Layer used? (A)They are of no use in
CNN.
(B)Dimension Reduction
(C)Object Recognition
(D)Image Sensing

Ans:B

14. Autoencoders are taught with the help of _____________________.


(A)Feed Forward
(B)Reconstruction
(C)Back Propagation
(D)They do not require Training

Ans:C

You might also like