MCQs

Disclaimer:

Educational Use Only:

The website links provided are to be used strictly for educational and knowledge-gaining purposes only.

No Misuse:

Do not misuse the links or the information contained therein for any commercial, illegal, or unethical activities.

Respect for Websites and Businesses:

Respect the intellectual property and business interests of the websites and their owners. Do not attempt to alter, copy, or redistribute content without proper authorization.

Acknowledge Value of Knowledge:

Recognize and value the knowledge and resources shared by these websites. Use the information responsibly and ethically.

No Endorsement:

The provision of these links does not imply endorsement of the linked sites, their content, or their products and services. Users are responsible for evaluating the suitability and accuracy of the information.

User Responsibility:

By accessing these links, you agree to use the information at your own risk and to comply with all applicable laws and website terms of use.

Overall MCQs for Reference

What is the primary purpose of a Support Vector Machine?
a. Data reduction
b. Dimensionality reduction
c. Classification and regression
d. Clustering
Answer: cwikipedia+2
In SVM, what is a hyperplane?
a. A curve
b. A line segment
c. A decision boundary separating classes
d. A cluster center
Answer: cgeeksforgeeks+1
The closest points to the hyperplane in SVM are called:
a. Margins
b. Support vectors
c. Centroids
d. Boundaries
Answer: bgeeksforgeeks+2
What does SVM aim to maximize?
a. Number of support vectors
b. Training accuracy
c. The margin between classes
d. Model complexity
Answer: ccmu+3
Which kernel is used for linearly inseparable data?
a. Linear kernel
b. Non-linear kernel
c. Radial Basis Function (RBF) kernel
d. Sigmoid kernel
Answer: cscikit-learn+1
In SVM, what is the function of the kernel trick?
a. Reducing data size
b. Transforming data to higher dimensions
c. Pruning noisy samples
d. Optimizing weights
Answer: bcourse.ccs.neu+2
What does a large value of regularization parameter C in SVM indicate?
a. Wider margin, allows more misclassification
b. Narrower margin, penalizes misclassification
c. Unchanged margin
d. Makes model less sensitive to outliers
Answer: bgeeksforgeeks+1
Which of the following SVM kernels is best suited for image classification?
a. Linear
b. Polynomial
c. RBF
d. Sigmoid
Answer: cscikit-learn+1
What is soft margin in SVM?
a. No margin at all
b. Margin allowing misclassification
c. Margin with no outlier tolerance
d. Infinite margin
Answer: bcsethings+1
Slack variables in SVM are used for:
a. Increasing overfitting
b. Decreasing support vectors
c. Allowing misclassification for noisy data
d. Reducing computation time
Answer: ccsethings+1
What does the SVM algorithm do for binary classification?
a. Minimizes correlation
b. Finds a single optimal line or hyperplane separating two classes
c. Reduces data redundancy
d. Maximizes variance
Answer: bibm+2
The optimal separating hyperplane in SVM is:
a. Arbitrary
b. Closest to one class
c. Farthest from support vectors of both classes
d. Randomly chosen
Answer: cgeeksforgeeks+1
SVM can be used for:
a. Only classification
b. Only regression
c. Both classification and regression
d. Clustering only
Answer: clingayasvidyapeeth+2
The equation for a linear SVM hyperplane is:
a.
b.
c.
d.
Answer: bcourse.ccs.neu+1
What principle does SVM use to achieve better generalization?
a. Empirical risk minimization
b. Statistical risk minimization
c. Maximum likelihood
d. Structural risk minimization
Answer: dwikipedia+1
SVMs are especially powerful for:
a. Low-dimensional data
b. High-dimensional data
c. Only 2D data
d. Balanced datasets only
Answer: bwikipedia+1
What are support vectors?
a. Points randomly selected for training
b. Points closest to the decision boundary
c. Noise points
d. Points farthest from decision boundary
Answer: bmit+2
Which problems can be handled by SVM?
a. Only linear classification
b. Linear and non-linear classification
c. Only non-linear classification
d. Only supervised clustering
Answer: bgeeksforgeeks+2
The kernel function in SVM:
a. Maps data to a lower dimension
b. Discards outliers
c. Maps data to a higher dimension
d. Always uses a sigmoid function
Answer: csciencedirect+2
What is the margin in SVM?
a. The area between data points
b. Distance between support vectors and the hyperplane
c. The sum of weights
d. The product of bias and weights
Answer: bgeeksforgeeks+2
Which SVM variant allows for non-separable data using penalty term?
a. Hard margin SVM
b. Soft margin SVM
c. Linear SVM
d. Polynomial SVM
Answer: bcsethings+1
What is the role of Lagrange multipliers in SVM?
a. Data normalization
b. Solving the dual formulation
c. Feature selection
d. Dimension reduction
Answer: bcourse.ccs.neu+1
For multi-class classification, SVM uses:
a. One-vs-One and One-vs-All strategies
b. Only hard margin
c. Stochastic gradient descent
d. Lossless encoding
Answer: asciencedirect+1
The RBF kernel is also known as:
a. Gaussian kernel
b. Sigmoid kernel
c. Linear kernel
d. Polynomial kernel
Answer: ascikit-learn+1
What does the parameter gamma in SVM affect?
a. The bias term
b. Kernel coefficient in RBF/polynomial kernels
c. Output feature size
d. Number of classes
Answer: bgeeksforgeeks+1
SVMs help control overfitting by:
a. Increasing bias
b. Limiting feature count
c. Maximizing the margin
d. Ignoring training error
Answer: cwikipedia+2
If all data points are correctly separable, which SVM is used?
a. Hard margin
b. Soft margin
c. Fuzzy SVM
d. None of these
Answer: ageeksforgeeks+1
In SVM, removing a support vector would:
a. Not change the hyperplane
b. Change the hyperplane
c. Increase accuracy always
d. Reduce margin to zero
Answer: bwayground+1
What is the typical use of the sigmoid kernel?
a. Regression tasks only
b. Emulating neural networks
c. Only for linear separation
d. Removing outliers
Answer: bscikit-learn+1
SVMs are best suited for datasets that are:
a. Small or medium with high dimensionality
b. Huge with low dimensionality
c. Large with many missing values
d. Sequential/time series only
Answer: awikipedia+1
VC theory in SVM refers to:
a. Vapnik-Chervonenkis theory
b. Variable Clustering
c. Vector Combination
d. Variance Calculation
Answer: acourse.ccs.neu+1
What happens if C is set too low in SVM?
a. Wide margin, more misclassifications allowed
b. No margin
c. Margin is forced through outliers
d. Model always underfits
Answer: ageeksforgeeks+1
The primal form in SVM optimization solves for:
a. Kernel parameters
b. Directly the weights and bias of hyperplane
c. Support vectors only
d. Only kernel coefficients
Answer: bcourse.ccs.neu+1
When using kernels, SVM can:
a. Only find linear boundaries
b. Separate non-linearly separable data
c. Only apply to numeric data
d. Ignore feature scaling
Answer: bscikit-learn+2
The function that measures distance between data points in SVM is called:
a. Support function
b. Kernel function
c. Margin
d. Probability function
Answer: bcourse.ccs.neu+1
The dual problem in SVM allows:
a. Use of kernels and easier computation for high-dimensional data
b. Only regression support
c. Increased number of support vectors
d. Only binary classification
Answer: asciencedirect+2
Which SVM kernel works well if data are linearly separable?
a. RBF
b. Polynomial
c. Linear
d. Sigmoid
Answer: cgeeksforgeeks+1
What is the decision function’s output in SVM?
a. Always 1 or 0
b. Signed distance to the hyperplane
c. Class label as text
d. Probability score
Answer: bgeeksforgeeks+1
How does SVM perform with large datasets?
a. Very fast training
b. Prone to out-of-memory
c. May be slower, but still effective for high dimensional data
d. Ignores irrelevant features
Answer: cwikipedia+1
Which is NOT an advantage of SVM?
a. Handles high dimensional data
b. Memory inefficiency with large samples
c. Robust against overfitting
d. Effective even when number of features > number of samples
Answer: bscikit-learn+1
Overfitting in SVM can be mitigated by:
a. Increasing C arbitrarily
b. Decreasing C and using soft margin
c. Avoiding kernels
d. Increasing model complexity
Answer: bgeeksforgeeks+1
Feature scaling is important in SVM because:
a. Kernels are sensitive to magnitude
b. Output is categorical
c. SVM ignores feature size
d. Reduces number of features
Answer: ageeksforgeeks+1
When is One-vs-One strategy efficient in SVM?
a. When classes are more than 5
b. When classes are fewer and dataset is small
c. For only binary classification
d. For time series data
Answer: bscikit-learn+1
SVM is a _____ learning algorithm.
a. Supervised
b. Unsupervised
c. Reinforcement
d. Semi-supervised
Answer: aibm+1
SVM margin violations (errors) are penalized by:
a. Kernel function only
b. Slack variables
c. Feature scaling
d. Primal variables
Answer: bcsethings+1
Which of the following can NOT be used as an SVM kernel?
a. Polynomial
b. Gaussian
c. Linear
d. K-Means
Answer: dgeeksforgeeks+1
SVMs were invented by:
a. Geoffrey Hinton
b. Vladimir Vapnik and Alexey Chervonenkis
c. Andrew Ng
d. Yann LeCun
Answer: bwikipedia+1
The output of SVM for a test data point is determined by:
a. Majority class in dataset
b. Distance from the hyperplane
c. Class with highest probability
d. Support vector count
Answer: bgeeksforgeeks+1
The support vectors for SVM:
a. Are not important
b. Are the only samples determining the model
c. Are randomly chosen points
d. Don’t influence model output
Answer: bmit+2
In Scikit-learn, SVMs can be used for:
a. Classification only
b. Regression only
c. Classification, regression, and outlier detection
d. Only clustering
Answer: cscikit-learn

Blog

Systemethic Technologies

Leave a Reply Cancel reply

Useful links

Other Terms & Policies

Contact Info