Major links



Quicklinks


📌 Quick Links
[ DBMS ] [ SQL ] [ DDB ] [ ML ] [ DL ] [ NLP ] [ DSA ] [ PDB ] [ DWDM ] [ Quizzes ]


Showing posts with label Machine Learning Quiz. Show all posts
Showing posts with label Machine Learning Quiz. Show all posts

Wednesday, January 14, 2026

Top Machine Learning MCQs with Detailed Answers | Perceptron, SVM, Clustering & Neural Networks

✔ Scroll down and test yourself — answers are hidden under the “View Answer” button.

☰ Quick Links - Browse Related MCQs
🚨 Quiz Instructions:
Attempt all questions first.
✔️ Click SUBMIT at the end to unlock VIEW ANSWER buttons.
Quiz Mode:
1.
Consider a Perceptron that has two input units and one output unit, which uses an LTU activation function, plus a bias input of +1 and a bias weight w3 = 1. If both inputs associated with an example are 0 and both weights, w1 and w2, connecting the input units to the output unit have value 1, and the desired (teacher) output value is 0, how will the weights change after applying the Perceptron Learning rule with learning rate parameter α = 1? [University of Wisconsin–Madison, CS540-2: Introduction to Artificial Intelligence, May 2018 - Final exam answers]







Correct Answer: D

What is perceptron?

A Perceptron is the simplest type of artificial neural network and is used for binary classification problems. It works like a decision-making unit that takes multiple inputs, multiplies each input by a weight, adds a bias, and then produces an output.

Mathematically, the perceptron computes a weighted sum of inputs and passes it through an activation function:

Perceptron Weight Update Using the Perceptron Learning Rule - Answer explained

Given:

  • Inputs: x1 = 0, x2 = 0
  • Bias input: x3 = +1
  • Initial weights: w1 = 1, w2 = 1, w3 = 1
  • Learning rate (α) = 1
  • Desired (teacher) output: t = 0
  • Activation function: Linear Threshold Unit (LTU)

Step 1: Net Input Calculation

net = w1x1 + w2x2 + w3x3
net = (1 × 0) + (1 × 0) + (1 × 1) = 1

Step 2: Actual Output

Since net ≥ 0, the LTU output is:
y = 1

Step 3: Error Calculation

error = t − y = 0 − 1 = −1

Step 4: Weight Update (Perceptron Learning Rule)

winew = wi + α(t − y)xi

Updated weights:

  • w1new = 1 + (1)(−1)(0) = 1
  • w2new = 1 + (1)(−1)(0) = 1
  • w3new = 1 + (1)(−1)(1) = 0

Final Answer

After applying the Perceptron Learning Rule, the updated weights are:

  • w1 = 1
  • w2 = 1
  • w3 = 0

Explanation: Since both input values are zero, the input weights remain unchanged. The perceptron incorrectly produced an output of 1, so the bias weight is reduced to lower the net input in future predictions.

2.
consider a dataset containing six one-dimensional points: {2, 4, 7, 8, 12, 14}. After three iterations of Hierarchical Agglomerative Clustering using Euclidean distance between points, we get the 3 clusters: C1 = {2, 4}, C2 = {7, 8} and C3 = {12, 14}.? [University of Wisconsin–Madison, CS540: Introduction to Artificial Intelligence, October 2019 - Midterm exam answers]







Correct Answer: A

Merge Using Single Linkage in Hierarchical Clustering

In Single Linkage hierarchical clustering, the distance between two clusters is defined as the minimum distance between any pair of points, one from each cluster.

Given Clusters

  • C1 = {2, 4}
  • C2 = {7, 8}
  • C3 = {12, 14}

Inter-Cluster Distance Calculations

Distance between C1 and C2:

min{|2 − 7|, |2 − 8|, |4 − 7|, |4 − 8|} = min{5, 6, 3, 4} = 3

Distance between C2 and C3:

min{|7 − 12|, |7 − 14|, |8 − 12|, |8 − 14|} = min{5, 7, 4, 6} = 4

Distance between C1 and C3:

min{|2 − 12|, |2 − 14|, |4 − 12|, |4 − 14|} = min{10, 12, 8, 10} = 8

Conclusion

The smallest inter-cluster distance is d(C1, C2) = 3. Therefore, using Single Linkage, the clusters C1 and C2 are merged in the next iteration.

Resulting cluster: {2, 4, 7, 8}

3.
Which of the following are true of support vector machines? [University of California at Berkeley, CS189: Introduction to Machine Learning, Spring 2019 - Final exam answers]







Correct Answer: A

What does the hyperparameter C mean in SVM?

In a soft-margin Support Vector Machine, the hyperparameter C controls the trade-off between:

  • Maximizing the margin (simpler model)
  • Minimizing classification error on training data

Explanation of each option

Option A — TRUE
Increasing the hyperparameter C penalizes misclassified training points more heavily, forcing the SVM to fit the training data more accurately.
➜ Training error generally decreases.
Option B — FALSE
Hard-margin SVM allows no misclassification and corresponds to C → ∞, not C = 0.
➜ With C = 0, misclassification is not penalized.
Option C — FALSE
Increasing C makes the classifier fit the training data more strictly.
➜ Training error decreases, not increases.
Option D — FALSE
A large C forces the decision boundary to accommodate even outliers.
➜ Sensitivity to outliers increases, not decreases.

Final Answer: Only Option A is true.

Exam Tip: Think of C as the cost of misclassification. High C → low training error but high sensitivity to outliers.

4.
Which of the following might be valid reasons for preferring an SVM over a neural network? [Indian Institute of Technology Delhi, ELL784: Introduction to Machine Learning, 2017 - 18 - Exam answers]







Correct Answer: B
Kernel SVMs can implicitly operate in infinite-dimensional feature spaces via the kernel trick, while neural networks have finite-dimensional parameterizations.

Option (b):
An SVM can effectively map the data to an infinite-dimensional space; a neural net cannot.

The key idea here comes from the kernel trick. Kernel-based SVMs (such as those using the RBF kernel) implicitly operate in an infinite-dimensional Hilbert space.

  • This mapping is done implicitly, without explicitly computing features.
  • The number of learned parameters does not grow with the feature space.
  • The optimization problem remains convex, guaranteeing a global optimum.

In contrast, neural networks:

  • Operate in finite-dimensional parameter spaces (finite neurons and weights).
  • Do not truly optimize over an infinite-dimensional feature space.
  • Require explicit architectural growth to approximate higher complexity.

SVMs can exactly work in infinite-dimensional feature spaces via kernels, whereas neural networks can only approximate such mappings using finite architectures.

Why other options are INCORRECT?

  • Option (a) — Incorrect: Neural networks can also learn non-linear transformations through hidden layers and activation functions.
  • Option (c) — Incorrect: Unlike neural networks, SVMs solve a convex optimization problem and do not get stuck in local minima.
  • Option (d) — Incorrect: The implicit feature space created by SVM kernels is typically harder—not easier—to interpret than neural network representations.
5.
Suppose that you are training a neural network for classification, but you notice that the training loss is much lower than the validation loss. Which of the following is the most appropriate way to address this issue? [Stanford University, CS224N: Natural Language Processing with Deep Learning Winter 2018 - Midterm exam answers]






Correct Answer: C

What does "training loss is much lower than the validation loss" mean?

A large gap between training and validation loss is a strong indicator of overfitting, where the model has low bias but high variance.

When the training loss is much lower than the validation loss, it means:

  • The model is learning the training data too well, including noise and minor patterns.
  • It fails to generalize to unseen data (validation set).
  • In other words, the network performs well on seen data but poorly on new data.

Why this happens

  • The model is too complex (too many layers or neurons).
  • Insufficient regularization (e.g., low dropout, weak L2 penalty).
  • Limited training data to learn generalized patterns.
  • Training for too many epochs, allowing memorization of the training set.

Explanation: Why option C is correct?
A much lower training loss compared to validation loss indicates overfitting. Increasing the L2 regularization weight penalizes large model weights, discourages overly complex decision boundaries, and improves generalization to unseen data.

Why the other options are incorrect

  • Option A — Incorrect: Decreasing dropout reduces regularization and typically worsens overfitting.
  • Option B — Incorrect: Increasing hidden layer size increases model capacity, making overfitting more likely.
  • Option D — Incorrect: Adding more layers increases complexity and usually amplifies overfitting.

Note: When training loss ≪ validation loss, think regularization, simpler models, or more data.

6.
Traditionally, when we have a real-valued input attribute during decision-tree learning we consider a binary split according to whether the attribute is above or below some threshold. Pat suggests that instead we should just have a multiway split with one branch for each of the distinct values of the attribute. From the list below choose the single biggest problem with Pat’s suggestion: [Carnegie Mellon University, 10-701/15-781 Final, Fall 2003 - Final exam answers]






Correct Answer: C

How Decision Trees Handle Real-Valued Attributes

Traditional Approach (Binary Split)

For a real-valued attribute A, decision trees choose a threshold t and split the data as:

  • A ≤ t
  • A > t

This approach groups nearby values together, allowing the model to learn general patterns while keeping the decision tree simple and robust.

Pat’s Suggestion

Pat proposes using a multiway split, with one branch for each distinct value of the real-valued attribute.

If the attribute has many unique values (which is very common for real-valued data), this would create many branches—potentially one branch per training example.

What Goes Wrong?

1. Perfect Memorization of Training Data

  • Each training example can end up in its own branch
  • Leaf nodes become extremely “pure”
  • The decision tree effectively memorizes the training set

👉 This usually results in very high (sometimes perfect) training accuracy.

2. Very Poor Generalization

  • Test data often contains values not seen during training
  • Even very close numeric values are treated as completely different
  • The model cannot generalize across ranges of values

👉 This leads to poor performance on the test set.

Why Option (iii) Is the Biggest Problem

  • Option (i) Too computationally expensive ❌
    Multiway splits increase complexity, but learning is still feasible and this is not the main issue.
  • Option (ii) Bad on both training and test ❌
    Incorrect, because training performance is usually very good.
  • Option (iii) Good on training, bad on test ✅ (Correct)
    This is a classic case of overfitting, where the model learns noise and exact values instead of true patterns.
  • Option (iv) Good on test, bad on training ❌
    Highly unlikely for a decision tree with this much flexibility.

Final Conclusion

Pat’s approach causes severe overfitting:

  • Excellent training accuracy
  • Poor generalization to unseen data

Therefore, the correct answer is:

(iii) It would probably result in a decision tree that scores well on the training set but badly on a test set.

7.
For a neural network, which one of these structural assumptions is the one that most affects the trade-off between underfitting (i.e. a high bias model) and overfitting (i.e. a high variance model): [Carnegie Mellon University, 10-701/15-781 Final, Fall 2003 - Final exam answers]






Correct Answer: A

The question is about model capacity / complexity, which directly controls the bias–variance trade-off.

Key Concept: Bias–Variance Trade-off

High Bias (Underfitting)

  • Model is too simple
  • Cannot capture underlying patterns

High Variance (Overfitting)

  • Model is too complex
  • Fits noise in the training data

The main factor controlling this trade-off is how expressive the model is.

Evaluating Each Option

Option (i) The Number of Hidden Nodes (Correct)

  • It determines how many parameters the network has
  • It controls how complex a function the network can represent
  • Few hidden nodes → simple model → high bias (underfitting)
  • Many hidden nodes → complex model → high variance (overfitting)

Overall, this directly controls the bias–variance trade-off.

Option (ii) The Learning Rate ❌

Affects training speed and convergence stability but does not change the model’s capacity or bias–variance behavior.

Option (iii) The Initial Choice of Weights ❌

Influences which local minimum is reached, but not the network structure or overall model complexity.

Option (iv) The Use of a Constant-Term Unit Input (Bias Unit) ❌

Allows shifting of activation functions, but has only a minor effect compared to the number of hidden nodes.

8.
Select the true statements about k-means clustering. Assume no two sample points are equal. [University of California at Berkeley, CS189: Introduction to Machine Learning, Spring 2025 - Final exam answers]






Correct Answer: D

The question asks you to select the true statements about k-means clustering, specifically about Lloyd’s Algorithm, which is the standard algorithm used to solve k-means.

k-means is greedy, initialization-dependent, centroid-based, and increasing k never increases the optimal cost.

Answer explanation:

Key assumptions given:
  • No two sample points are equal (this avoids tie cases but does not change the main conclusions).
  • We are reasoning about the k-means objective (cost) function, usually the sum of squared distances from points to their assigned cluster centroids.

Correct Answer: D

Increasing the number of clusters k can never increase the global minimum of the k-means cost function.

Why this is true:

  • When k increases, the algorithm has more freedom to place centroids closer to the data points.
  • The optimal cost for k + 1 clusters is never worse than for k clusters. In the worst case, we could reuse the same clustering as before.
  • Since the number of data points is greater than the number of clusters, each cluster can contain at least one point, so the objective function remains valid.

Formally:
J*(k + 1) ≤ J*(k)

In the extreme case: k = n (one cluster per point) → each point is its own centroid → cost = 0.

Note: This statement is about the global minimum, not the solution found by Lloyd’s algorithm in practice, which may get stuck in a local minimum.


Why other options are wrong?

  • Option A: Lloyd’s finds local minima, not global ❌
  • Option B: Average linkage ≠ k-means ❌
  • Option C: Initialization affects results ❌
9.
For very large training data sets, which of the following will usually have the lowest training time? [University of Pennsylvania, CIS 520: Machine Learning, 2019 - Final exam answers]






Correct Answer: C

“KNN has almost zero training cost because it does not learn a model; it only stores the data.”


Option-by-option explanation

  • ❌ Logistic Regression: Training involves iterative optimization (gradient descent, Newton methods). Cost per iteration is 𝑂(𝑛⋅𝑑). Needs many passes over the data. Not the fastest for very large datasets.
  • ❌ Neural Networks: Training requires multiple epochs and backpropagation. Computationally very expensive. Training time increases rapidly with: Data size, Number of layers. and Number of neurons. One of the slowest to train.
  • ✅ K-Nearest Neighbors (KNN): KNN has essentially no training phase. Training consists of simply storing the dataset in memory. No optimization, no model fitting. Training time is approximately O(1) (or linear time to store data). Lowest training time, especially for very large datasets. ⚠️ Note: Prediction time is expensive, but that is not asked here
  • ❌ Random Forests: Training involves building many decision trees. Each tree performs recursive splits. Training cost grows quickly with number of trees, depth of trees, and dataset size. Slow to train on very large datasets.
10.
In building a linear regression model for a particular data set, you observe the coe cient of one of the features having a relatively high negative value. This suggests that [Indian Institute of Technology Madras (IITM), Introduction to Machine Learning, Quiz answers]






Correct Answer: C

In linear regression, coefficient magnitude alone does not determine feature importance unless features are on comparable scales.

A high magnitude suggests that the feature is important. However, it may be the case that another feature is highly correlated with this feature and its coefficient also has a high magnitude with the opposite sign, in effect cancelling out the effect of the former. Thus, we cannot really remark on the importance of a feature just because its coefficient has a relatively large magnitude.


Why other options are wrong?

  • Option A: The magnitude of a coefficient alone is misleading. Without knowing feature scaling, units, correlation with other features, regularization used etc., you cannot conclude that the feature has a “strong effect”. ❌
  • Option B: A high-magnitude coefficient (even negative) indicates that the model is sensitive to that feature. Ignoring the feature based only on the sign or raw magnitude is unjustified. ❌

Frequently Asked Questions (Machine Learning)

What does it mean when training loss is much lower than validation loss?

When training loss is much lower than validation loss, it indicates that the model is overfitting. The model has learned the training data very well, including noise, but fails to generalize to unseen data. This usually occurs due to high model complexity or insufficient regularization.

Why does using a multiway split for real-valued attributes in decision trees cause problems?

Using a multiway split for real-valued attributes creates many branches, often one per unique value. This leads to overfitting, where the decision tree performs very well on training data but poorly on test data because the splits capture noise rather than general patterns.

Which machine learning algorithm has the lowest training time for very large datasets?

K-nearest neighbors (KNN) usually has the lowest training time because it does not learn an explicit model. Training simply involves storing the data, while most computation happens during prediction.

Does Lloyd’s algorithm for k-means clustering find the global minimum?

No, Lloyd’s algorithm does not guarantee finding the global minimum of the k-means objective function. It converges to a local minimum that depends on the initial choice of cluster centroids.

Does increasing the number of clusters (k) in k-means always reduce the cost function?

Increasing the number of clusters cannot increase the global minimum of the k-means cost function as long as the number of data points is greater than the number of clusters. The cost is non-increasing as k increases because additional clusters allow equal or better fitting of the data.

How should a large negative coefficient be interpreted in linear regression?

A large negative coefficient indicates that the feature is negatively correlated with the target variable. However, the magnitude alone does not determine feature importance unless features are on comparable scales. Additional information such as feature normalization is required.

How does increasing the number of hidden nodes affect bias and variance?

Increasing the number of hidden nodes generally reduces bias but increases variance. While a more complex model can better fit the training data, it also becomes more prone to overfitting.

Why is feature scaling important when interpreting linear model coefficients?

Feature scaling makes coefficients comparable across features in linear models. Without scaling, features measured in smaller units may appear more important due to larger coefficient values, even if their true effect on the target variable is small.

Tuesday, January 6, 2026

Choosing the Right Machine Learning Algorithm – Real-World MCQs with Answers

✔ Scroll down and test yourself — answers are hidden under the “View Answer” button.

☰ Quick Links - Browse Related MCQs
🚨 Quiz Instructions:
Attempt all questions first.
✔️ Click SUBMIT at the end to unlock VIEW ANSWER buttons.

Choosing the Right Machine Learning Algorithm – Real-World MCQs

Selecting the correct machine learning algorithm is a critical step in solving real-world data science problems. The choice depends on factors such as data type, problem objective, labeled vs unlabeled data, and output nature.

In this quiz, you will explore scenario-based MCQs using real-life datasets from domains such as real estate, e-commerce, banking, healthcare, recommendation systems, and time-series forecasting. These questions are commonly asked in university exams, ML interviews, and competitive tests.

Topics covered include:

  • Regression vs Classification problems
  • Supervised vs Unsupervised learning
  • Clustering and Customer Segmentation
  • Recommendation Systems
  • Time-Series Forecasting
  • Dimensionality Reduction

Each question includes difficulty level, data type, and clear explanations to help you understand why a particular ML algorithm is the best choice.

House Price Prediction (Bangalore Real Estate)
1. A real-estate company wants to predict house prices in Bangalore using features such as area (sq.ft), number of bedrooms, location, and age of the building. The target value is continuous.






Correct Answer: B
Difficulty: Easy
Data Type: Labeled, Continuous Target

Linear Regression is ideal for predicting continuous numerical values.

Why not others? Logistic Regression is for classification, K-Means is unsupervised, and Apriori is for association rules.

Email Spam Detection (Gmail-like System)
2. An email service like Gmail wants to classify emails as Spam or Not Spam using word frequencies and sender information.






Correct Answer: D
Difficulty: Easy
Data Type: Labeled, Text Data

Naive Bayes works well for probabilistic text classification problems.

Why not others? K-Means is unsupervised and PCA is for dimensionality reduction.

Customer Segmentation for Amazon
3. Amazon wants to group customers based on purchase history, spending behavior, and browsing activity for marketing purposes.






Correct Answer: B
Difficulty: Medium
Data Type: Unlabeled, Numerical Features

K-Means clusters similar customers without requiring labeled data.

Why not others? Classification algorithms require predefined labels.

Credit Card Fraud Detection
4. A bank wants to detect fraudulent credit-card transactions where fraud cases are rare compared to normal transactions.






Correct Answer: B
Difficulty: Interview-level
Data Type: Labeled, Imbalanced Dataset

Random Forest handles non-linearity and class imbalance effectively.

Why not others? Linear Regression cannot model classification boundaries.

Movie Recommendation System (Netflix-Style)
5. Netflix wants to recommend movies based on users’ viewing history and ratings from similar users.






Correct Answer: B
Difficulty: Medium
Data Type: Labeled User–Item Interactions

Collaborative Filtering leverages similarities among users or items.

Why not others? Regression models do not capture preference similarity.

Predicting Customer Churn (Telecom Dataset)
6. A telecom company wants to predict whether a customer will churn based on usage patterns and complaint history.






Correct Answer: A
Difficulty: Easy
Data Type: Labeled, Binary Target

Logistic Regression is designed for binary classification problems.

Why not others? PCA reduces features but does not classify.

Handwritten Digit Recognition (MNIST Dataset)
7. A system must recognize handwritten digits (0–9) from the MNIST image dataset.






Correct Answer: C
Difficulty: Medium
Data Type: Labeled Image Data

CNNs learn spatial features crucial for image recognition.

Why not others? Traditional ML models cannot exploit image structure.

Product Demand Forecasting (Walmart Sales Data)
8. Walmart wants to forecast next month’s product sales using historical daily sales data.






Correct Answer: B
Difficulty: Medium
Data Type: Time-Dependent Numerical Data

ARIMA models temporal dependencies in sequential data.

Why not others? K-Means ignores time ordering.

Identifying Frequent Product Bundles (Market Basket Analysis)
9. A supermarket wants to identify products that are frequently purchased together.






Correct Answer: B
Difficulty: Easy
Data Type: Transactional Data

Apriori discovers association rules from transaction records.

Why not others? Classification models do not find item associations.

Reducing Features in a High-Dimensional Dataset
10. A dataset contains 1,000 features, and the goal is to reduce dimensionality before training a model.






Correct Answer: B
Difficulty: Easy
Data Type: High-Dimensional Numerical Data

PCA reduces features while preserving maximum variance.

Why not others? K-Means clusters data but does not reduce dimensions.

Thursday, December 4, 2025

10 Advanced Machine Learning MCQs with Answers & Explanations (Generative vs Discriminative, KDE, Boosting, k-NN)

✔ Scroll down and test yourself — answers are hidden under the “View Answer” button.

Hidden Markov Model - MCQs - Problem-based Practice Questions

Machine Learning - Advanced MCQs

Understanding the foundations of machine learning requires a strong grasp of how different models learn from data, make predictions, and generalize. This collection of MCQs covers essential concepts such as generative vs discriminative classification, k-NN behavior, MAP vs MLE estimation, boosting dynamics, kernel methods, and decision tree depth—topics frequently asked in exams, interviews, and university courses.

These questions are designed to strengthen conceptual clarity and test real-world intuition about model assumptions, probability distributions, density estimation, and decision boundaries.

Whether you are preparing for GATE, UGC NET, university assessments, data science interviews, or machine learning certifications, this curated set will help you quickly revise key principles and identify common pitfalls in ML theory.

1. In a generative classification model, once you estimate the class-conditional density P(X∣Y) and prior P(Y), the decision rule is obtained by:

Answer: B
Explanation:

Generative models estimate P(X∣Y) and P(Y). Classification is performed using Bayes’ rule: P(Y∣X) ∝ P(X∣Y)P(Y).

Generative models are a class of machine learning models that learn the underlying data distribution and can generate new data samples similar to those seen during training.

A generative model learns the joint probability distribution: 𝑃(𝑋,𝑌) or just 𝑃(𝑋). This means the model tries to understand how the data is produced, not just how to classify it.

2. Logistic regression and Gaussian Naive Bayes can produce identical decision boundaries under which condition?

Answer: A
Explanation:

GNB with shared identity covariance produces a linear discriminant identical to logistic regression’s functional form.

Understanding the Question

This question asks under which specific condition Logistic Regression (LR) and Gaussian Naive Bayes (GNB) classifiers produce identical decision boundaries. The key is understanding the mathematical relationship between these two seemingly different algorithms.

Both models, Logistic Regression (LR) and Gaussian Naïve Bayes (GNB) normally produce different decision boundaries because:

  • LR is discriminative → models 𝑃(𝑌∣𝑋). That is, Logistic Regression directly models the conditional probability 𝑃(𝑌∣𝑋) using the logistic function.
  • GNB is generative → models 𝑃(𝑋∣𝑌). That is, Gaussian Naive Bayes is a generative classifier that models the joint probability 𝑃(𝑋,𝑌) by estimating P(Y) and 𝑃(𝑋∣𝑌).

But under a special condition, they produce identical linear decision boundaries. That special condition is: When the covariances of all classes are identity and equal.

When GNB has: Identity covariance, that means, no correlation between features, each feature has variance=1 and same covariance for each class, Gaussian Naïve Bayes's decision boundary has the same mathematical form as Logistic Regression.

Both models produce: 𝑤𝑋+𝑏=0. Same functional form, so same separating hyperplane.
3. Which of the following best explains why the training error of 1-NN is always zero?

Answer: B
Explanation:

Each training sample is its own closest neighbor, so 1-NN always predicts correctly on training data.

What is 1-NN?

1-NN means 1-Nearest Neighbor, which is the simplest form of the k-Nearest Neighbors (k-NN) algorithm. 1-NN classifier assigns the class of a new point based on the single closest training point in the dataset.

Why is the training error of 1-NN always zero?

In 1-Nearest Neighbor classification, when predicting the label of a data point, the algorithm finds the closest point in the dataset. But if you test 1-NN on the same training data, then every training point’s nearest neighbor is itself (distance = 0). So the classifier simply returns its own label, which is always correct.

Thus: Training Error = 0, because no point is misclassified when it's compared with itself.
4. For which type of prior does the MAP estimate not converge to the MLE even with infinite data?

Answer: C
Explanation:

A degenerate (a.k.a. point-mass or delta) prior forces the parameter to a fixed value regardless of data, so MAP ≠ MLE even with infinite samples.

5. Cross-validation is useful in boosting primarily because:

Answer: A
Explanation:

Boosting can overfit if allowed to run indefinitely; CV selects the optimal number of rounds.

Boosting keeps improving training accuracy indefinitely and can easily overfit, so cross-validation is needed to decide how many boosting steps to perform.

What is boosting?

Boosting is a family of ensemble learning techniques that turn a collection of weak learners (models that are only slightly better than random guessing) into a single strong learner with high predictive accuracy. The core idea is simple: train models sequentially, each one focusing on the mistakes made by the previous ones, and then combine their predictions (usually by a weighted vote or sum). By doing this, the ensemble corrects its own errors over time and ends up far more powerful than any individual component.

What is cross-validation?

Cross-validation is a fundamental resampling technique used to evaluate machine learning models' ability to generalize to unseen data while preventing overfitting. It works by systematically partitioning the dataset into multiple subsets (called folds), training models on some subsets, and testing on others, with this process repeated multiple times to obtain a reliable performance estimate.

Why does boosting need cross-validation?

Boosting algorithms (like AdaBoost, Gradient Boosting, XGBoost, etc.) build models sequentially, adding weak learners (usually decision stumps/trees) one at a time.

Unlike many other models:
  • There is no built-in rule that tells you when to stop adding more learners.
  • If you keep boosting longer, the model can overfit heavily.
So, to choose the right number of boosting rounds, we use cross-validation. Cross-validation helps to decide: How many weak learners give the best performance without overfitting?

This is why libraries like XGBoost include a parameter like early_stopping_rounds, which depends on a validation set.

6. Kernel Density Estimation (KDE) differs from kernel regression because:

Answer: A
Explanation:

KDE estimates P(X), while kernel regression estimates the functional relationship ŷ(x) via weighted averages.

Differences between KDE and Kernel regression


What each method estimates/answers:
  • KDE answers "what is the probability density?" (it answers, 'how are the data distributed?')
  • Kernel regression answers "what is the function value or conditional expectation?" (it answers, 'Given X, what is Y?')
How kernels are used?
  • KDE uses kernels to smooth the estimated probability distribution,
  • Kernel regression uses kernels to perform weighted local averaging to estimate a conditional relationship between variables.
When to use?
  • Use Kernel Density Estimation when you want to understand how the data is distributed, especially when you do NOT assume the distribution is normal. Example: Estimate the density of customer ages
  • Use kernel regression when you want to predict Y from X in a non-parametric, smooth way.
Supervised vs Unsupervised
  • KDE is unsupervised
  • Kernel regression is supervised
7. Boosting a set of weak learners generally produces a decision boundary that is:

Answer: B
Explanation:

Boosting aggregates many weak rules, often resulting in highly nonlinear decision boundaries.

How does boosting affect the complexity of the final decision boundary?

Boosting (e.g., AdaBoost, Gradient Boosting) works by combining many weak learners, typically simple classifiers like decision stumps (depth-1 trees). Each weak learner itself has a simple decision boundary.

But boosting does not just average them; it takes a weighted combination based on each learner’s accuracy. Adding many simple boundaries creates a final decision boundary that can be very complex, often highly nonlinear.

This happens because each new weak learner focuses on misclassified points from previous learners, gradually bending the overall decision surface.

8. Which scenario explains how a decision tree can exceed training samples in depth?

Answer: B
Explanation:

If identical feature vectors map to conflicting labels, the tree keeps splitting and can exceed depth n.

Why can a decision tree have depth greater than the number of training samples?

Because depth counts the number of splits along a path, not the number of unique samples or unique feature values. Even if features repeat, the tree keeps splitting as long as it can reduce impurity—possibly creating long chains of binary splits, each separating a subset of samples, even if they have identical feature values.

Why does this happen with repeated features?

When features repeat across multiple samples:
  • The tree must use the same features repeatedly to separate conflicting labels.
  • Each split on a feature that has been previously split becomes less efficient at separating classes.
  • The tree exhibits overfitting behavior, attempting to memorize individual samples rather than learn generalizable patterns.
  • If samples are identical in their selected features but have different labels, the tree becomes unable to achieve purity through feature thresholds alone

Decision trees try to make leaves pure. If purity is impossible, depth grows uncontrollably. This is why real systems use: max_depth, min_samples_split, min_samples_leaf.

To avoid pathological overfitting trees.

Example:

When the feature values are repeated (e.g. many rows have x = 5) but the labels differ, the tree may keep trying thresholds that slice right at the repeated value. If the algorithm does not enforce a “strictly decreasing impurity” condition, it could accept a split that leaves the dataset unchanged on one side.

9. In k-NN classification, which statement best explains why increasing k (while keeping the dataset fixed) can improve test performance, especially in noisy datasets?

Answer: A
Explanation:

When k increases, the prediction is based on a majority vote over a larger set of neighbors, which reduces the influence of mislabeled or noisy points. This typically improves generalization by lowering variance, although extremely large k can lead to underfitting.

Larger k reduces sensitivity to noise by averaging over more neighbors.
  • Averaging = majority vote – By looking at several nearby points instead of just one, the classifier “averages” their labels. If a few of those neighbours are mislabeled (or are outliers), they are unlikely to dominate the vote.
  • Noise reduction – Random fluctuations in the training labels act like noise. Majority voting behaves like a low‑pass filter: it suppresses high‑frequency (noisy) variations while preserving the underlying signal.
  • Result on test error – Lower variance ⇒ the learned decision surface is more stable on unseen data, so test error typically goes down (up to a point; if k becomes too large, bias dominates and performance can deteriorate).

Thus, averaging over more neighbours mitigates the effect of noisy or atypical training points, which is why test performance usually improves.

10. Which statement about generative vs discriminative models is correct?

Answer: B
Explanation:

Discriminative models learn P(Y∣X) or direct decision boundaries. Generative models learn P(X,Y).

Please visit, subscribe and share 10 Minutes Lectures in Computer Science

Featured Content

Multiple choice questions in Natural Language Processing Home

MCQ in Natural Language Processing, Quiz questions with answers in NLP, Top interview questions in NLP with answers Multiple Choice Que...

All time most popular contents