Department of Computer Science and Engineering

Artificial and Computational Intelligence

M.Tech. I Year I Term
Course Objectives
• To provide students with a strong foundation in artificial intelligence (AI) and
computational intelligence (CI) techniques.
• To introduce advanced concepts such as deep learning, natural language processing, and
reinforcement learning for solving real-world problems.
• To develop the ability to model complex systems using AI and CI approaches like fuzzy
systems, genetic algorithms, and neural networks.
• To enable students to implement AI and CI algorithms using modern tools and frameworks
in domains such as healthcare, robotics, and natural language processing.
• To sensitize students to the ethical, social, and economic implications of AI and CI
technologies in society.
Syllabus
Module – I
Introduction to Artificial and computational Intelligence
Definition, Scope, and Goals of AI, Intelligent Agents: Types, Structure, and Environments,
Computational Intelligence.
Lab Tasks:
1. Research and present how AI is applied in different domains like agriculture, healthcare,
finance, home automation and robotics.
2. Create a comparison table for various CI techniques like Artificial Neural Networks (ANN),
Genetic Algorithms (GAs), Particle Swarm Optimization (PSO), Ant Colony Optimization
(ACO), Fuzzy Logic with respect to their applications and strengths.
Module – II
Heuristic Search Techniques
Problem-Solving as Search: Uninformed Search Strategies (DFS, BFS).
Informed Search Strategies: A* Search, Greedy Best-First Search, Adversarial Search: Minimax
Algorithm, Alpha-Beta Pruning, Constraint Satisfaction Problems (CSPs): Backtracking and Local
Search.
Lab Tasks:
1. Implement A* search to solve a pathfinding problem in a grid with obstacles.
2. Solve a Sudoku puzzle using backtracking or implement a local search method to solve
CSPs.
Module – III
Knowledge Representation and Reasoning
Knowledge-Based Systems: Propositional Logic, First-Order Logic, Ontologies and Semantic
Networks, Reasoning Under Uncertainty: Probabilistic Reasoning, Bayesian Networks.
Lab Tasks:
1. Implement a truth table generator for a given logical expression and check its satisfiability.
2. Implement a simple Bayesian network to calculate the probability of an event given some
evidence.
Module – IV
Data Exploration
Data Types, Data Pre-processing, Supervised, Unsupervised, and Reinforcement Learning,
Comparative analysis with examples.
Lab Tasks:
1. Implement a pre-processing technique for binary classification using a dataset
(e.g., Iris dataset), and visualize the decision boundary.
2. Implement both supervised (e.g., logistic regression) and unsupervised learning
(e.g., k-means clustering) on a dataset and compare the results.
Module – V
Evolutionary Algorithms
Genetic Algorithms (GAs), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO).
Lab Tasks:
1. Implement a genetic algorithm to solve an optimization problem (e.g., the traveling
salesman problem).
2. Implement and compare GA, PSO, and ACO on a common optimization problem (other
than the problem considered above) and analyse their performance.
Module – VI
Fuzzy Systems
Fuzzy Logic: Membership Functions, Fuzzy Sets, Fuzzy Rules, Fuzzy Inference Systems,
Applications of Fuzzy Systems in Real-World Problems.
Lab Tasks:
1. Implement a fuzzy logic controller for a system like automatic temperature control.
2. Design a fuzzy inference system for an application like a traffic control system based on
fuzzified input.
Module – VII
Deep Learning
Deep Learning Basics: Introduction to Deep Neural Networks, Convolutional Neural Networks
(CNNs) and Applications, Recurrent Neural Networks (RNNs), Long Short-Term Memory
(LSTM).
Lab Tasks:
1. Use a pre-trained CNN (like VGG or ResNet) and fine-tune it for a custom image
classification task.
2. Implement an LSTM model for time-series prediction or sentiment analysis.
Module – VIII
Natural Language Processing
Introduction to NLP: Text Preprocessing, Tokenization, Lemmatization.
Applications of NLP: Sentiment Analysis, Chatbots, Text Summarization.
Advanced Topics: Transformer Models.
Lab Tasks:
1. Implement text preprocessing including tokenization, lemmatization, and removing stop
words on a given dataset.
2. Design and implement a simple chatbot.
Module – IX
Reinforcement Learning
Markov Decision Processes (MDPs), Q-Learning and Deep Q-Networks (DQN).
Applications: Robotics, Game AI, Self-Learning Systems.
Lab Tasks:
1. Implement a Q-learning agent for solving a maze or a grid-world problem.
2. Implement DQN for a game-like environment (e.g., CartPole) using a neural network as the
function approximator.
Module – X
Advanced Topics in Artificial and Computational Intelligence
Explainable AI (XAI): Importance and Techniques, Computational Creativity: Generative
Adversarial Networks (GANs), Ethical and Social Implications of AI and CI.
Lab Tasks:
1. Implement a GAN to generate images (e.g., from noise to MNIST digits).
2. Write a report or case study on the ethical and societal implications of AI in areas like
surveillance, privacy, and autonomous weapons.
Course Outcomes
• Students will be able to apply fundamental and advanced AI techniques to design intelligent
systems.
• Students will demonstrate the ability to analyze complex problems and solve them using
heuristic and optimization methods.
• Students will create and implement machine learning and deep learning models using
appropriate tools and frameworks.
• Students will be capable of building intelligent applications in areas such as vision,
language processing, and decision-making.
• Students will critically evaluate AI solutions for efficiency, scalability, and ethical impact
on society and industries.

Text Books
• "Artificial Intelligence: A Modern Approach" by Stuart Russell and Peter Norvig.
• "Pattern Recognition and Machine Learning" by Christopher M. Bishop.
• "Fuzzy Logic with Engineering Applications" by Timothy J. Ross.

*****