### **UNIT – I: Introduction to Machine Learning**

1. **What is Artificial Intelligence?**

- Artificial Intelligence (AI) is the field of computer science that focuses on

creating systems that can perform tasks requiring human intelligence, such
as problem-solving, learning, and decision-making.

2. **Define Machine Learning.**

- Machine Learning (ML) is a subset of AI that enables computers to learn

from data and improve their performance on a task without being explicitly
programmed.

3. **Differentiate supervised and unsupervised learning.**

- **Supervised learning** uses labeled data to train models, while

**unsupervised learning** finds patterns in unlabeled data without
predefined outputs.

4. **What is rote learning in ML?**

- Rote learning refers to memorization without understanding, where an ML

model recalls previously seen data without generalizing.

5. **Give any two examples of real-world ML applications.**

- **Spam detection in emails** and **recommendation systems (e.g.,

Netflix, Amazon).**

6. **What does feature engineering involve?**

- Feature engineering involves selecting, transforming, or creating features

from raw data to improve the performance of ML models.
7. **Define the term “data representation.”**

- Data representation refers to how data is structured and formatted to be

processed effectively by ML models.

8. **What is model evaluation in ML?**

- Model evaluation assesses the performance of an ML model using metrics

like accuracy, precision, and recall.

9. **State one key characteristic of reinforcement learning.**

- Reinforcement learning involves an agent that learns optimal actions

through rewards and penalties.

10. **List any two common types of data used in ML.**

- **Numerical data (e.g., age, temperature)** and **Categorical data (e.g.,

gender, color).**

### **UNIT – II: Distance-Based Learning**

1. **Define a distance measure in the context of ML.**

- A distance measure quantifies the similarity or dissimilarity between two

data points.

2. **What is a proximity measure?**

- A proximity measure calculates how close two objects are in a given

feature space.

3. **What is the k-NN (k-Nearest Neighbor) classifier?**

- k-NN is a non-parametric algorithm that classifies a data point based on

the majority class of its k nearest neighbors.
4. **Mention any two commonly used distance metrics.**

- **Euclidean distance** and **Manhattan distance.**

5. **State one key difference between Euclidean and Manhattan distance.**

- Euclidean distance measures straight-line distance, while Manhattan

distance measures distance along grid-like paths.

6. **Define a non-metric similarity function.**

- A non-metric similarity function does not strictly follow distance

properties (e.g., cosine similarity).

7. **Mention one advantage of the k-NN algorithm.**

- k-NN is simple and requires no training phase.

8. **What is meant by “radius neighbor” in distance-based classification?**

- A radius neighbor considers all points within a fixed radius instead of a

fixed number of neighbors.

9. **Define k-NN regression.**

- k-NN regression predicts a continuous value by averaging the values of its

k nearest neighbors.

10. **Give one real-world application of distance-based classification.**

- **Handwritten digit recognition (e.g., MNIST dataset).**

### **UNIT – III: Decision Trees & Random Forests**

1. **Define a decision tree.**

- A decision tree is a hierarchical model that splits data into branches

based on feature conditions to make decisions.

2. **What is an impurity measure in decision trees?**

- Impurity measures (e.g., entropy, Gini index) quantify how mixed or pure
a node is in a decision tree.

3. **State two examples of impurity measures used in decision trees.**

- **Entropy** and **Gini Index.**

4. **Define “information gain.”**

- Information gain measures the reduction in entropy after splitting a

dataset based on a feature.

5. **What is the Gini index?**

- The Gini index measures the probability of incorrectly classifying a

randomly chosen element.

6. **Mention one advantage of using decision trees.**

- Decision trees are easy to interpret and visualize.

7. **Define “Random Forest.”**

- A Random Forest is an ensemble learning method that combines multiple

decision trees to improve accuracy.

8. **What is a leaf node in a decision tree?**

- A leaf node represents a final decision/output in the tree structure.

9. **Define the term “entropy” in the context of decision trees.**

- Entropy is a measure of randomness or impurity in a dataset.

10. **Mention one difference between classification trees and regression

trees.**

- **Classification trees predict categorical values, whereas regression trees

predict continuous values.**

### **UNIT – IV: Linear Models & SVM**

1. **What is a linear discriminant in Machine Learning?**

- A linear discriminant is a function that separates different classes using a

straight decision boundary.

2. **Define the perceptron learning algorithm.**

- The perceptron learning algorithm updates weights based on errors to

classify data using a linear decision boundary.

3. **Mention any one key assumption behind Support Vector Machines

(SVMs).**

- The data is assumed to be linearly separable in high-dimensional space.

4. **What is the basic idea of the Perceptron as a linear classifier?**

- The perceptron classifies data by learning a weighted sum of features and

applying a threshold.

5. **Define “kernel trick” in the context of SVMs.**

 - The kernel trick transforms input space to a higher-dimensional space to
make non-linearly separable data linearly separable.

6. **State one difference between logistic regression and linear regression.**

- Logistic regression predicts probabilities, while linear regression predicts

continuous values.

7. **What does the term “activation function” refer to in an MLP?**

- An activation function determines the output of a neuron in a neural

network.

8. **Define “hyperplane” in the context of linear classification.**

- A hyperplane is a decision boundary that separates different classes in a

feature space.

9. **Mention one advantage of using SVM for classification.**

- SVMs are effective in high-dimensional spaces.

10. **What is “bias term” in linear regression models?**

- The bias term allows the model to fit data that does not pass through the
origin.

### **UNIT – V: Clustering**

1. **What is clustering in the context of Machine Learning?**

- Clustering is the task of grouping similar data points without predefined

labels.

2. **Differentiate clustering from classification in one key point.**

 - **Classification** uses labeled data, whereas **clustering** finds patterns
in unlabeled data.

3. **Mention one difference between hierarchical and partitional clustering.**

- Hierarchical clustering creates a tree-like structure, while partitional

clustering divides data into fixed groups.

4. **Define “k-Means clustering.”**

- k-Means is a clustering algorithm that partitions data into k clusters based

on centroids.

5. **What is fuzzy clustering?**

- Fuzzy clustering assigns data points to multiple clusters with varying

degrees of membership.

6. **Give one example of a distance measure used in clustering.**

- **Euclidean distance.**

7. **Name one advantage of hierarchical clustering.**

- It does not require predefining the number of clusters.

8. **Define “cluster center” in k-Means clustering.**

- The cluster center is the mean of all data points in a cluster.

9. **Mention one difference between crisp clustering and fuzzy clustering.**

- **Crisp clustering** assigns each data point to only one cluster, whereas
**fuzzy clustering** allows partial membership.
10. **State one real-world application of clustering.**

- **Customer segmentation in marketing.**

---