23AD2001R Lab Workbook
23AD2001R Lab Workbook
23AD2001R Lab Workbook
&
MACHINE LEARNING
23AD2001A/E
LAb WORKbOOK
STUDENT ID:
STUDENT NAME:
Mission
To impart quality higher education and to undertake research and
extension with emphasis on application and innovation that cater to
the emerging societal needs through all-round development of the
students of all sections enabling them to be globally competitive and
socially responsible citizens with intrinsic values.
CONTENTS
Experiment Name Page
8. IMPLEMENTATION OF INFERENCING 32
The laboratory framework includes a creative element but shifts the time-intensive aspects outside
of the two-hour closed laboratory period. Within this structure, each laboratory includes three
parts: Pre-Lab, In-Lab, Post-Lab.
a. Pre-Lab:
The pre-lab exercise is a homework assignment that links the lecture with the laboratory
period – typically takes 2 hours to complete. The goal is to synthesize the information they
learn in lecture with material from their textbook to produce a working piece of software.
Students attending a two-hour closed laboratory are expected to make a good faith e ort
to complete the pre-lab exercise before coming to the lab. Their work need not be perfect,
but their e ort must be real.
b. In-Lab:
The in-lab section takes placed during the actual laboratory period. The first hour of the
laboratory period can be used to resolve any problems the students might have experienced
in completing the pre-lab exercises. The intent is to give constructive feedback so that
students leave the lab with working pre-lab software – a significant accomplishment on
their part. During the second hour, students complete the in-lab exercise to reinforce the
concepts learnt in the pre-lab. Students leave the lab having received feedback on their pre-
lab and in-lab work.
c. Post-Lab:
The last phase of each laboratory is a homework assignment that is done following the
laboratory period. In the post-lab, students analyze the e iciency or utility of a given system
call. Each post-lab exercise should take roughly 120 minutes to complete.
This structure not only reinforces the concepts learned but also enhances students' practical
abilities. The approach ensures continuous engagement with the material, promoting a well-
rounded educational experience. Overall, the framework e ectively bridges theoretical learning
and practical application, fostering both knowledge and skill development.
2024-25 ODD SEMESTER CONTINUOUS EVALUATION – LAB EXERCISE
In-Lab
S. Pre-Lab (25M) Post-Lab Viva Total Faculty
No.
Date Experiment (10M) Procedure Result Inference (10M) (5M) (50M) Signature
(5M) (10M) (10M)
8 Implementation of Inferencing
Description:
This experiment introduces the foundational concepts of Python programming. Installation
procedure for Jupyter Notebook, understanding basic Python syntax and data types, implementing
control flow, and using fundamental data structures.
Prerequisites:
Basic understanding of what programming is and familiarity with using a computer.
Pre-Lab:
1. What is a variable in Python, and how do you assign a value to it?
4. What are the di erent types of loops available in Python, and when would you use
each?
Page 1 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
5. Define a list and a dictionary in Python and provide an example of when each might
be used.
In-Lab:
Procedure/Program:
1. Basic Syntax and Data Types:
Write a program to calculate the sum of two numbers and print the result. Create
variables of di erent data types (integer, float, string, Boolean) and print their values.
2. Control Flow:
Write a program that checks whether a number is even or odd.
Page 2 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
3. Data Structures:
Write a Python program to demonstrate the use of lists, tuples, dictionaries, and sets,
and print them.
Page 3 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Create a grade report generator that categorizes students into grade brackets (A, B, C, etc.) and
generates a summary report. (no need to use function)
Viva Voce:
1. Explain how variables are declared and used in Python.
2. What are some common data types in Python, and how do they di er?
Page 4 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
5. Give an example of a situation where using a list would be more appropriate than a
dictionary.
Page 5 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
This experiment focuses on modular programming in Python, which involves organizing code into
reusable components called modules, import built-in and third-party modules, and use functions to
encapsulate and reuse code. The experiment also covers file handling techniques, including reading
from and writing to text files. Understanding these concepts is crucial for developing e icient and
organized Python programs, as they allow for better code management, reuse, and interaction with
external data.
Prerequisites:
Basic knowledge of Python syntax, data types, and control flow. Familiarity with the concepts of
functions and basic programming structures is also recommended.
Pre-Lab:
1. What is a module in Python, and why is it useful?
3. Explain the di erence between ‘import’ and ‘from ... import ...’ in Python.
Page 6 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
5. What are the common file modes in Python, and what do they mean?
In-Lab:
Procedure/Program:
1. Libraries and Modules:
Write a Python program that imports and uses functions from standard libraries such as
math and random. (sqrt, random)
2. Functions:
Write a Python program that defines and calls a function for calculating the factorial of a
number.
Page 7 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
3. File Handling:
Write a Python program to read from and write to a file.
Page 8 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Write a python program to read data from a file and display its content using pandas library, display
it using pyplot module in matplotlib
Viva Voce:
1. How do you define a function in Python, and what is the purpose of parameters?
Page 9 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
3. How can you pass arguments to a function in Python, and what is the significance of
default parameters?
4. Discuss the importance of closing a file after performing file operations and how
this can be achieved in Python.
Page 10 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
This experiment focuses on the application of data science methods, including data cleaning,
exploratory data analysis, and visualization. Use of various tools to process and visualize data, and
then implement machine learning algorithms to derive insights or make predictions, demonstrating
the importance of each step in the data science workflow and the impact of visualization and
machine learning on understanding complex datasets.
Prerequisites:
Basic understanding of statistics, data handling, and programming in Python. Familiarity with data
visualization libraries (e.g., Matplotlib, Seaborn) and machine learning libraries (e.g., Scikit-learn) is
beneficial.
Pre-Lab:
1. What are the key steps in the data science workflow?
Page 11 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
3. What are some common data visualization techniques and their uses?
In-Lab:
Procedure/Program:
1. Basic Data Science:
Load a dataset using Pandas and perform basic exploratory data analysis (EDA).
Page 12 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
2. Data Visualization:
Visualize the data using Matplotlib and Seaborn to understand the distributions and
relationships between variables.
Page 13 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Using "tips" dataset, which is a built-in dataset available in the seaborn library, demonstrate basic
data visualization techniques using Python libraries: ‘pandas’, ‘seaborn’, and ‘matplotlib’.
Page 14 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. Explain the role of data preprocessing in data science.
2. What are the steps involved in performing exploratory data analysis (EDA)?
4. What are some common types of plots used in Data Visualization? Explain them.
5. Describe the process of splitting a dataset into training and testing sets. Why is this
step important?
Page 15 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
Implement the BFS algorithm to traverse a graph and determine the shortest path from a specified
source node to a target node. BFS is a fundamental algorithm in graph theory that explores nodes
level by level and is particularly useful for finding the shortest path in unweighted graphs. The
experiment will be helpful in understanding graph traversal techniques, the concept of queues in
BFS, and how to represent graphs using adjacency lists or matrices.
Prerequisites:
Basic understanding of graph theory, including graph representation (adjacency list and adjacency
matrix). Familiarity with queues and basic algorithmic concepts is also required. Knowledge of
Python is necessary for implementing the algorithm.
Pre-Lab:
1. What is the purpose of the Breadth-First Search (BFS) algorithm in graph traversal?
Page 16 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
4. How can BFS be used to find the shortest path in an unweighted graph?
In-Lab:
Procedure/Program:
Page 17 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Implement Breadth-First Search (BFS) to find the path to reach the target from a source node given a
Maze
Page 18 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. How does BFS ensure that the shortest path is found in an unweighted graph?
4. What are the typical applications of the BFS algorithm in real-world scenarios?
Page 19 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
The A* search algorithm is a widely used pathfinding and graph traversal algorithm, known for its
e iciency in finding the shortest path from a starting point to a goal. In this experiment, you will
implement the A* algorithm to solve 15 puzzle problem using priority queue. The experiment will
illustrate key concepts such as heuristic functions, cost functions, and the role of the priority queue
in optimizing the search process.
Prerequisites:
Basic understanding of graph theory, including concepts like nodes, edges, and weights. Familiarity
with programming concepts such as data structures (lists, queues, priority queues) and basic
algorithms is essential.
Pre-Lab:
1. What is the A* search algorithm, and how does it di er from other search algorithms
like Dijkstra's algorithm?
2. What are heuristic functions, and why are they important in the A* algorithm?
Page 20 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
In-Lab:
Procedure/Program:
Page 21 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Implement A* search algorithm A* with BFS for solving the Salesperson problem.
Page 22 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. Explain how the A* algorithm ensures finding the shortest path.
2. What is the significance of the heuristic function being admissible in the A* algorithm?
4. How does A* handle the exploration of states with di erent task assignments?
5. How can the A* algorithm's performance be a ected by the choice of the heuristic
function?
Page 23 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
The Alpha-Beta pruning algorithm is an optimization technique for the minimax algorithm, commonly
used in two-player games like chess to reduce the number of nodes evaluated in the search tree. This
experiment involves implementing the Alpha-Beta pruning algorithm to a simplified version of a
chess game, focusing on scenarios like piece capture or checkmate detection. The experiment
demonstrates how Alpha-Beta pruning enhances the e iciency of the minimax algorithm by pruning
branches that cannot influence the final decision, thereby speeding up the computation.
Prerequisites:
Basic understanding of game theory, particularly the minimax algorithm, and fundamental
programming skills. Familiarity with chess rules and strategies, as well as data structures like trees
and recursion, will be beneficial.
Pre-Lab:
1. What is the minimax algorithm, and how is it used in decision-making for two-player
games?
3. What is the significance of the 'alpha' and 'beta' values in the Alpha-Beta pruning
algorithm?
Page 24 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
4. Explain how pruning in the Alpha-Beta algorithm a ects the search process.
In-Lab:
Procedure/Program:
Page 25 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Implement Alpha Beta Pruning Algorithms for a Decision support system.
Page 26 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. How does the alpha-beta pruning technique optimize the Minimax algorithm?
2. What is the di erence between "alpha" and "beta" cuto s in the algorithm?
4. How does the AI determine the best move using the Minimax algorithm in this
simulation?
5. Discuss the potential impact of move ordering on the e iciency of the Alpha-Beta
pruning algorithm.
Page 27 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
This experiment will explore the use of Constraint Satisfaction Problem (CSP) algorithms to solve
cryptographic arithmetic puzzles, where letters represent digits in a mathematical equation. The task
involves implementing a CSP algorithm that assigns digits to letters such that the arithmetic equation
is satisfied. This experiment highlights the key concepts of CSP, including variables, domains, and
constraints using backtracking and heuristic methods to e iciently explore potential solutions and
analyze the algorithm's performance in terms of solution time and accuracy. The experiment also
provides insights into the applications of CSP algorithms in various fields, including cryptography
and artificial intelligence.
Prerequisites:
Foundational knowledge of algorithms, data structures (such as graphs and trees), and basic
concepts in cryptography. Familiarity with backtracking, heuristics, and problem-solving techniques
in computer science is essential.
Pre-Lab:
1. What is a Constraint Satisfaction Problem (CSP), and how is it formulated?
3. What are cryptographic arithmetic problems, and how do they relate to CSPs?
Page 28 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
5. What are some common heuristics used to improve the e iciency of CSP
algorithms?
In-Lab:
Procedure/Program:
Page 29 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Implement CSP Algorithm for an n-Queen problem using forward-checking
Page 30 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. What is a Constraint Satisfaction Problem (CSP), and how is it relevant to resource
allocation?
2. How would you apply CSP techniques to production planning to optimize the use of
machinery and labor?
3. What are some common CSP solving techniques used for resource allocation
problems?
5. How would you evaluate the performance of a CSP solution for resource allocation?
Page 31 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
8. Implementation of Inferencing
AIM:
To design and implement a home security system model using propositional logic and forward-
checking techniques to simulate logical reasoning and threat detection.
Description:
This experiment involves creating a model for a home security system that utilizes propositional logic
to represent various security components and potential threats. Implementation of a system where
sensors (e.g., for motion, doors, windows) provide inputs, and propositional logic rules are used to
determine the state of the system (e.g., secure, alert). Forward-checking will be used to ensure that
all constraints are satisfied and to proactively manage sensor states, preventing false alarms and
ensuring system reliability. This exercise provides hands-on experience with logical reasoning,
system design, and the practical application of forward-checking in constraint satisfaction
scenarios.
Prerequisites:
Familiarity with the basics of propositional logic, including logical operators and truth tables.
Knowledge of constraint satisfaction problems, particularly the forward-checking technique, and
programming experience are essential.
Pre-Lab:
1. What is propositional logic, and how is it used to represent conditions and rules?
2. Explain the role of sensors in a home security system and how their data can be
represented using propositional logic.
Page 32 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
5. What are some common challenges in designing a logical system for security
purposes?
In-Lab:
Procedure/Program:
Page 33 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Implement Inferencing using forward chaining when logic is expressed in FOL.
Page 34 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. How can propositional logic be used to solve problems or make decisions?
4. How does the resolution method work in predicate logic, and how is it applied in
inference?
5. What are some common reasoning techniques used in predicate logic for a
knowledge representation system?
Page 35 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
The Naïve Bayes classifier is a probabilistic machine learning algorithm based on Bayes' theorem,
with an assumption of independence between features using the Iris dataset, which contains
measurements of sepal length, sepal width, petal length, and petal width for three species of iris
flowers: Iris-setosa, Iris-versicolor, and Iris-virginica. The goal is to train a Naïve Bayes classifier using
this data and then predict the species label for new, unseen data. This experiment will help you
understand the principles of probabilistic classification, the handling of categorical and continuous
data, and the practical steps involved in training and evaluating a classifier.
Prerequisites:
Basic understanding of probability theory, Bayes' theorem, and the concept of independence in
statistics. Familiarity with machine learning concepts, data preprocessing, and programming skills
in Python (using libraries such as scikit-learn) are essential.
Pre-Lab:
1. What is the Naïve Bayes classifier, and how does it work?
3. How is Bayes' theorem applied in the context of the Naïve Bayes classifier?
Page 36 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
4. What are the main features and labels in the Iris dataset?
In-Lab:
Procedure/Program:
Page 37 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Implement a Naïve Bayes classifier to Determine whether a passenger on the Titanic survived or not,
given some features like their gender and their age.
Page 38 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. Describe how the Naïve Bayes classifier calculates the probability of a class given
the input features.
2. What are the limitations of the Naïve Bayes classifier, especially concerning the
independence assumption?
3. How does the Naïve Bayes classifier handle continuous data versus categorical
data?
4. Discuss the significance of feature scaling in the context of the Naïve Bayes
classifier.
5. How would you improve the accuracy of a Naïve Bayes classifier if the initial results
are unsatisfactory?
Page 39 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
A Bayesian network is a graphical model that represents a set of variables and their conditional
dependencies through a directed acyclic graph. In this experiment, you will construct a Bayesian
network to detect the likelihood of a burglary in a given scenario. The network will include variables
such as burglary, alarm system status, police response, and neighbors' observations. By assigning
conditional probabilities to each node, you will use the network to infer the probability of a burglary
given observed evidence, such as an alarm being triggered or a neighbor reporting suspicious activity.
This experiment provides hands-on experience with probabilistic reasoning, the construction of
Bayesian networks, and the application of Bayes' theorem in real-world scenarios.
Prerequisites:
Foundational understanding of probability theory, including conditional probability and Bayes'
theorem. Knowledge of graph theory particularly directed acyclic graphs, and familiarity with basic
concepts in artificial intelligence and machine learning will be beneficial.
Pre-Lab:
1. What is a Bayesian network, and what are its key components?
Page 40 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
4. How can Bayesian networks be used to update beliefs based on new evidence?
In-Lab:
Procedure/Program:
Page 41 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Implement a Bayesian Network for diagnosing patient conditions based on the symptoms.
Page 42 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. Describe the process of constructing a Bayesian network for a specific problem,
such as detecting a burglary.
2. How do you determine the conditional probabilities for the nodes in a Bayesian
network?
5. How can the accuracy and reliability of a Bayesian network model be evaluated?
Page 43 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
Logistic regression is a statistical method used for binary classification, predicting the probability of
a binary outcome based on one or more predictor variables. In this experiment, you will implement a
logistic regression model to detect network failures, such as downtime or significant performance
degradation. The model will use features extracted from network tra ic data, such as packet loss
rate, latency, and throughput, to predict the likelihood of a network failure. By training the model on
historical data, you will evaluate its performance in identifying potential failures before they occur,
thereby enhancing network reliability. This experiment will cover data preprocessing, feature
selection, model training, and evaluation using metrics such as accuracy, precision, recall, and the
ROC curve.
Prerequisites:
Basic understanding of regression analysis, binary classification, and logistic regression principles.
Familiarity with data preprocessing, statistical metrics, and programming skills (especially in Python,
using libraries such as pandas, scikit-learn, and matplotlib) is essential.
Pre-Lab:
1. What is logistic regression, and how is it used for binary classification?
Page 44 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
In-Lab:
Procedure/Program:
Page 45 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Implement a Purchase prediction model within an e-commerce system using a Logistic regression.
Page 46 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. Explain the logistic function and its role in logistic regression.
5. What are some limitations of using logistic regression for network failure detection?
Page 47 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Description:
The decision tree algorithm is a popular machine learning method for classification tasks. It involves
splitting the data into subsets based on feature values, creating a tree-like model of decisions. In this
experiment, you will use the Play Tennis dataset, which includes features such as outlook,
temperature, humidity, and wind conditions, to predict the target variable: whether to play tennis or
not. The goal is to construct a decision tree model that captures the relationships between these
features and the decision outcome. The experiment will cover the construction of the decision tree,
visualization, interpretation of the tree structure, and evaluation using metrics like accuracy,
precision, and recall. You will also explore concepts such as overfitting, pruning, and the importance
of feature selection.
Prerequisites:
Basic understanding of decision tree algorithms, including concepts like information gain and
entropy. Familiarity with data preprocessing, machine learning concepts, and programming skills
(especially in Python, using libraries like scikit-learn and pandas) is essential.
Pre-Lab:
1. What is a decision tree, and how is it used for classification?
2. Explain the concept of information gain and its role in building decision trees.
Page 48 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
4. How can overfitting occur in decision trees, and what techniques are used to
prevent it?
5. What are the features of the Play Tennis dataset, and what is the target variable?
In-Lab:
Procedure/Program:
Page 49 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Post-Lab:
Develop a Program for reducing the dimensions of a given data using PCA.
Page 50 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
DATE ….../……/………...
Viva Voce:
1. Describe the process of constructing a decision tree from a dataset.
2. How does the choice of features a ect the performance of a decision tree?
5. Discuss the advantages and limitations of using decision trees for classification
tasks.
Page 51 of 56
23AD2001A/E: ARTIFICIAL INTELLIGENCE & MACHINE LEARNING