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

Which normalization technique scales data to a range between 0 and 1?
a. Z-score normalization
b. Min-Max normalization
c. Decimal scaling
d. Robust scaling
Answer: b. Min-Max normalizationdevelopers.google+2
What is the main purpose of data normalization in machine learning?
a. Increase training size
b. Reduce variance
c. Standardize feature scaling
d. Remove outliers
Answer: c. Standardize feature scalingstudocu+2
Z-score normalization transforms data such that it has:
a. Mean = 0, Std dev = 1
b. Range = 0 to 1
c. Only positive values
d. Random distribution
Answer: a. Mean = 0, Std dev = 1codecademy+1
Which method is preferable when the dataset contains outliers?
a. Min-Max normalization
b. Decimal scaling
c. Z-score normalization
d. One-hot encoding
Answer: c. Z-score normalizationcodecademy
When using min-max normalization, which formula is applied?
a.
b.
c.
d.
Answer: c. geeksforgeeks+2
Decimal scaling normalization involves:
a. Subtracting the mean
b. Adding a constant
c. Dividing by
d. Taking the log
Answer: c. Dividing by geeksforgeeks
Which normalization constraint ensures each feature contributes equally to the result?
a. Non-negativity
b. Unit norm
c. Feature scaling
d. Linear dependence
Answer: c. Feature scalingdevelopers.google+1
In which scenarios is normalization especially required?
a. When data is already standardized
b. In distance-based algorithms
c. During categorical encoding
d. For all binary features
Answer: b. In distance-based algorithmsstudocu+1
Which technique reduces skewness by compressing large values?
a. Z-score normalization
b. Log transformation
c. Robust scaling
d. Min-max normalization
Answer: b. Log transformationgeeksforgeeks
Which constraint should be checked before normalization?
a. Missing values
b. Feature correlation
c. Class imbalance
d. Perfect separability
Answer: a. Missing valuesstudocu+1
What is a constraint in data preprocessing for machine learning?
a. Parameter initialization
b. Limitation or rule applied to data
c. Output variable
d. Training time limit
Answer: b. Limitation or rule applied to datasanfoundry+1
Which normalization technique is not affected much by outliers due to median-based scaling?
a. L1 normalization
b. Log transform
c. Robust scaling
d. Min-max scaling
Answer: c. Robust scalingcodecademy+1
When should normalization parameters (like mean/std) be computed?
a. On test data only
b. On the whole dataset
c. Only on training data
d. On target variable
Answer: c. Only on training datacodecademy
What is unit vector normalization also called?
a. One-hot encoding
b. L2 normalization
c. Mean normalization
d. Label encoding
Answer: b. L2 normalizationgeeksforgeeks
Which constraint does min-max normalization impose on data?
a. Zero mean
b. Range bounded between 0 and 1
c. Maximum variance
d. Gaussian shape
Answer: b. Range bounded between 0 and 1developers.google+2
Why is normalization important when using KNN?
a. Reduces memory
b. Features must have similar scales
c. Removes outliers
d. Avoids overfitting
Answer: b. Features must have similar scalesstudocu+1
Which transformation reduces feature range to less than 1 by dividing with a power of 10?
a. Min-max
b. Log
c. Decimal scaling
d. Z-score
Answer: c. Decimal scalinggeeksforgeeks
What is the key constraint for numerical data normalization?
a. All input must be binary
b. Preserving relative feature differences
c. Always mean zero
d. All features categorical
Answer: b. Preserving relative feature differencesdevelopers.google+1
What happens if categorical data is normalized?
a. Improved accuracy
b. Logical error, as normalization is for numerical
c. Faster convergence
d. Increased skewness
Answer: b. Logical error, as normalization is for numericalstudocu+1
A normalization technique that keeps mean at 0 and standard deviation at 1 is:
a. Unit vector
b. Min-max
c. Z-score
d. Log scaling
Answer: c. Z-scoredevelopers.google+1
Why should normalization not be applied to categorical features?
a. Categorical don’t have order/magnitude
b. Expensive computation
c. It increases accuracy
d. Makes data non-invertible
Answer: a. Categorical don’t have order/magnitudecodecademy+1
Which algorithm needs normalization most critically due to its distance calculations?
a. Decision Trees
b. Random Forest
c. K-Means
d. Naive Bayes
Answer: c. K-Meansdevelopers.google+1
What is the effect of normalization on gradient descent?
a. Slows convergence
b. Speeds convergence
c. Reduces loss
d. Prevents overfitting
Answer: b. Speeds convergencestudocu+1
Which technique is used to stabilize variance in features?
a. Outlier removal
b. Log transformation
c. Reducing data
d. Min-max scaling
Answer: b. Log transformationgeeksforgeeks
What will happen if normalization is skipped while features are of different scales?
a. Results will be robust
b. Larger scale features dominate
c. Prevents model learning
d. No effect
Answer: b. Larger scale features dominatestudocu+1
Which normalization method is used for features normally distributed?
a. Min-max scaling
b. One-hot encoding
c. Z-score scaling
d. Feature crossing
Answer: c. Z-score scalingcodecademy+1
Which is not a normalization constraint?
a. Scaling between set bounds
b. Maintaining the mean
c. Encoding labels
d. Standard deviation adjustment
Answer: c. Encoding labelscodecademy+1
What is a safe preprocessing step for features with unknown scaling?
a. Min-max normalization
b. Label encoding
c. Ignoring transformation
d. Z-score normalization
Answer: d. Z-score normalizationdevelopers.google+1
Which normalization affects the shape of feature distribution least?
a. Min-max
b. Decimal scaling
c. Log scaling
d. Z-score
Answer: a. Min-maxcodecademy
The constraint of “feature independence” in normalization refers to:
a. Features should be correlated
b. Features not influencing each other’s scaling
c. Features must be binary
d. Features are normalized together
Answer: b. Features not influencing each other’s scalingdevelopers.google+1
Which normalization is best for neural network input layers?
a. One-hot
b. Min-max
c. Z-score
d. Label encoding
Answer: b. Min-maxstudocu+1
Which is a constraint for applying normalization?
a. Features must be continuous
b. Features must be ordinal
c. Features must be categorical
d. Features must be missing
Answer: a. Features must be continuousstudocu+1
What is the purpose of “unit norm” normalization?
a. Minimize sum
b. Make vector length one
c. Outlier removal
d. Ensure mean is zero
Answer: b. Make vector length onegeeksforgeeks
Data normalization helps in:
a. Reducing training size
b. Equal feature contribution
c. Maximizing feature range
d. Lowering categorical effects
Answer: b. Equal feature contributiondevelopers.google+2
Why should the same normalization transformation be applied to test data as training?
a. For consistency and accurate inference
b. To increase data size
c. To introduce randomness
d. For faster computation
Answer: a. For consistency and accurate inferencecodecademy
What kind of constraint does normalization introduce to machine learning models?
a. Data format
b. Consistent feature scaling
c. Output range
d. Categorical mapping
Answer: b. Consistent feature scalingdevelopers.google+1
Which of the following is not a normalization technique?
a. Z-score normalization
b. Min-max normalization
c. Log scaling
d. One-hot encoding
Answer: d. One-hot encodinggeeksforgeeks
What normalization constraint is indirectly set by principal component analysis (PCA)?
a. Mean centering features
b. Maximum scaling
c. Binary range
d. Feature crossing
Answer: a. Mean centering featuresdiptisurvase.wordpress+1
Which is a side effect of min-max normalization on outliers?
a. Skewed feature range
b. Stable variance
c. Ignoring mean
d. Robustness to outliers
Answer: a. Skewed feature rangegeeksforgeeks+1
What is required prior to normalization if data contains extreme outliers?
a. Apply directly
b. Outlier treatment
c. Class balancing
d. Label encoding
Answer: b. Outlier treatmentstudocu+1
In which situation is normalization least beneficial?
a. Features are already the same scale
b. Features are continuous
c. Different units
d. Distance-based methods
Answer: a. Features are already the same scalecodecademy+1
What is the mathematical property imposed by L2-norm normalization?
a. Average equals zero
b. Dot product is constant
c. Length of vector = 1
d. Sum equals one
Answer: c. Length of vector = 1geeksforgeeks
Why is mean normalization rarely preferred over z-score or min-max?
a. Doesn’t scale variance
b. Too robust
c. Hard to compute
d. Only for categorical
Answer: a. Doesn’t scale variancedevelopers.google+1
Log normalization is commonly used for:
a. Data with high skew
b. Binary features
c. Already scaled features
d. Categorical encoding
Answer: a. Data with high skewgeeksforgeeks
What is the effect of skipping normalization on SVM with RBF kernel?
a. Model unaffected
b. Some features dominate
c. Faster convergence
d. Reduces test error
Answer: b. Some features dominatestudocu+1
Which method is NOT a constraint-based normalization method?
a. Z-score normalization
b. PCA mean-centering
c. One-hot encoding
d. Min-max normalization
Answer: c. One-hot encodinggeeksforgeeks
Normalization should not be fit on:
a. Training data
b. Test data
c. Combined training and test
d. Training or validation
Answer: b. Test datacodecademy
The constraint that “all features must be comparable” is handled by:
a. Normalization
b. Label encoding
c. Random sampling
d. Data shuffling
Answer: a. Normalizationstudocu+2
Which technique best preserves original data distribution?
a. Min-max scaling
b. Log transformation
c. Z-score
d. Decimal scaling
Answer: a. Min-max scalingdevelopers.google+1
Why should scaling constraints vary between algorithms?
a. Some algorithms use raw value distances, some do not
b. Only neural nets require scaling
c. Encoding methods depend on scaling
d. All features must be binary
Answer: a. Some algorithms use raw value distances, some do notcodecademy+2

Blog

Systemethic Technologies

Leave a Reply Cancel reply

Useful links

Other Terms & Policies

Contact Info