G-E2HZ7JKCY4

Artificial Intelligence

Course Title: Artificial Intelligence

Course Code: CS-202
Credit Hours: 3 (2+1)
Prerequisites: Object-Oriented Programming

Course Learning Outcomes (CLOs):

At the end of the course, students will be able to:

  1. CLO1: Understand key components and concepts in the field of artificial intelligence, including knowledge-based systems and reasoning.
    Domain: Cognitive
    BT Level: 2 (Understanding)
    PLO: Engineering Knowledge
  2. CLO2: Implement classical artificial intelligence techniques such as search algorithms, game-playing strategies, and learning from examples.
    Domain: Cognitive
    BT Level: 3 (Applying)
    PLO: Problem Analysis
  3. CLO3: Analyze and evaluate artificial intelligence techniques for practical problem-solving and apply them to real-world scenarios.
    Domain: Cognitive
    BT Level: 4 (Analyzing)
    PLO: Design/Development of Solutions

Program Learning Objectives (PLOs):

  1. PLO1: Engineering Knowledge: Apply knowledge of mathematics, science, engineering fundamentals, and an engineering specialization to solve complex engineering problems.
  2. PLO2: Problem Analysis: Identify, formulate, research literature, and analyze complex engineering problems reaching substantiated conclusions using first principles of mathematics, natural sciences, and engineering sciences.
  3. PLO3: Design/Development of Solutions: Design solutions for complex engineering problems and design systems, components, or processes that meet specified needs with appropriate consideration for public health and safety, cultural, societal, and environmental considerations.
  4. PLO4: Individual and Team Work: Function effectively as an individual, and as a member or leader in diverse teams and in multi-disciplinary settings.

Course Contents and Weekly Breakdown:

Week 1: Introduction to Artificial Intelligence

This week serves as an introduction to Artificial Intelligence (AI), covering fundamental concepts, real-world applications, and knowledge-based systems. The objective is to provide students with a foundational understanding of AI and familiarize them with the tools needed for AI development.

Step 1: Lecture – Introduction to AI

Topics Covered:

  1. Definition of AI
    • Understanding what AI is and its significance.
    • Difference between weak AI and strong AI.
  2. Applications of AI
    • AI in Healthcare (diagnosis, robotic surgery, drug discovery)
    • AI in Finance (fraud detection, stock market prediction)
    • AI in Transportation (autonomous vehicles, route optimization)
    • AI in Customer Service (chatbots, virtual assistants)
    • AI in Education (personalized learning, grading automation)
  3. Types of AI
    • Reactive Machines
    • Limited Memory AI
    • Theory of Mind AI
    • Self-Aware AI
  4. Knowledge-Based Systems
    • Concept of expert systems
    • Rule-based systems vs. machine learning-based systems

Step 2: Reading Material

Students are required to read Chapter 1: “Introduction to AI” from:

📖 Artificial Intelligence: A Modern Approach by Russell and Norvig

🔹 Key Takeaways from the Chapter:

  • Historical background of AI
  • AI problem-solving approaches
  • Ethical concerns and challenges in AI development

Step 3: Assignment – AI Applications Report

Task: Write a brief report (500-700 words) on the applications of AI in various fields.

📌 Instructions:

  1. Choose at least three fields where AI is applied (e.g., healthcare, business, education).
  2. Explain how AI is transforming each field with examples.
  3. Discuss any ethical or societal challenges AI presents in these fields.
  4. Cite at least two sources (journal articles, books, or reliable web sources).

📍 Submission Format:

  • File Format: PDF or Word
  • Font: Times New Roman, 12 pt
  • Spacing: 1.5
  • Submission Deadline: End of Week 1

Step 4: Lab Work – Introduction to Python for AI Development

Objective: Students will set up their Python environment and install the necessary libraries for AI development.

Lab Activities:

🔹 1. Installing Python

🔹 2. Setting Up Virtual Environment (Recommended)

  • Open Command Prompt (Windows) or Terminal (Mac/Linux)
  • Run:shCopyEditpython -m venv ai_env
  • Activate the environment:
    • Windows:shCopyEditai_env\Scripts\activate
    • Mac/Linux:shCopyEditsource ai_env/bin/activate

🔹 3. Installing Essential AI Libraries

  • Install NumPy, Pandas, Matplotlib, and Scikit-learn using:shCopyEditpip install numpy pandas matplotlib scikit-learn
  • Verify installation by running:shCopyEditpython -c "import numpy; import pandas; import matplotlib; import sklearn; print('Libraries Installed Successfully!')"

🔹 4. Running a Basic Python Script

  • Open a new Python file (example.py) and write:pythonCopyEditprint("Welcome to AI Development!")
  • Run the script:shCopyEditpython example.py
  • Expected Output:cssCopyEditWelcome to AI Development!

Step 5: Lab Assignment – Python Environment Setup

📌 Task:

  1. Install Python and create a virtual environment.
  2. Install the required AI libraries.
  3. Run a Python script and take a screenshot of the output.

📍 Submission Format:

  • Submit a Word/PDF report with:
    • Screenshot of the installed Python environment.
    • Screenshot of the Python script execution output.
  • Submission Deadline: End of Week 1

✅ Expected Learning Outcomes

By the end of Week 1, students should be able to:
✔ Understand the basics of AI and its real-world applications.
✔ Explain different AI approaches and knowledge-based systems.
✔ Set up a Python environment for AI development.
✔ Install necessary libraries for AI programming.

Week 2: Reasoning and Knowledge Representation

  • Introduction to reasoning, knowledge representation techniques
  • Reading Material:
    • Chapter 2: “Knowledge Representation” from Artificial Intelligence: A Modern Approach
  • Assignment: Create knowledge representation models for different scenarios.
  • Lab Work: Implement basic knowledge representation techniques in Python.
  • Lab Assignment: Develop and test a simple knowledge-based system.

Week 3: Problem Solving by Searching (Part 1)

  • Topics Covered:
  • Informed Searching:
    • Informed search algorithms, also known as heuristic search methods, use additional knowledge beyond the problem definition. These methods prioritize paths that are likely to lead more quickly to the solution.
    • Examples:
      • A search algorithm (optimizes pathfinding using heuristics and cost)
      • Greedy Best-First Search (chooses paths that seem to lead most directly toward the goal based on heuristics)
  • Uninformed Searching:
    • Uninformed search algorithms (or blind search) explore the problem space without any additional information about how far a given state is from the goal.
    • Examples:
      • Breadth-First Search (BFS) (explores all nodes at the present depth level before moving to the next level)
      • Depth-First Search (DFS) (explores as far as possible along a branch before backtracking)
  • Heuristics:
    • A heuristic is a problem-solving strategy or rule of thumb that improves search efficiency by estimating how close a current state is to the goal state.
    • Commonly used heuristics in AI include:
      • Manhattan Distance: Used in grid-based pathfinding
      • Euclidean Distance: For continuous spaces or geometric problems
  • Reading Material:
  • Chapter 3: “Search Algorithms” from Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig.This chapter provides a thorough explanation of search strategies in AI, including how different algorithms work, their time complexity, and trade-offs between different types of searches.
  • Assignment:
  • Implement and Compare Search Algorithms:
    • Write Python code to implement and compare at least three different search algorithms (e.g., BFS, DFS, and A*).
    • Compare their performance on a specific problem like navigating a maze or solving the 8-puzzle problem.
    • Analyze the results in terms of time complexity, memory usage, and the number of steps to reach the goal.
  • Lab Work:
  • Coding BFS and DFS in Python:
    • Start by writing the basic structure for BFS and DFS algorithms.
    • Use sample graphs or grids as input to test and observe the behavior of these search methods.
    • Practice visualizing the search process (optional) using a tool like matplotlib or networkx in Python.
  • Lab Assignment:
  • Develop a Search-Based Application:

Week 4: Problem Solving by Searching (Part 2)

  • Minimax algorithm, alpha-beta pruning, game-playing strategies
  • Reading Material:
    • Chapter 4: “Game Playing” from Artificial Intelligence: A Modern Approach
  • Assignment: Implement the minimax algorithm and alpha-beta pruning.
  • Lab Work: Build a simple game-playing agent using these algorithms.
  • Lab Assignment: Create a game simulation with an AI opponent.

Week 5: Case Studies in AI

  • General Problem Solver, Eliza, Student, Macsyma
  • Reading Material:
    • Case studies from Artificial Intelligence: A Modern Approach
  • Assignment: Analyze the effectiveness of the case study systems.
  • Lab Work: Review and discuss the design of historical AI systems.
  • Lab Assignment: Implement a simple simulation of one of the case study systems.

Week 6: Learning from Examples

  • Introduction to learning from examples, basic concepts of machine learning
  • Reading Material:
    • Chapter 5: “Learning from Examples” from Artificial Intelligence: A Modern Approach
  • Assignment: Apply learning from examples to a dataset.
  • Lab Work: Implement basic machine learning algorithms in Python.
  • Lab Assignment: Create a classification model using a sample dataset.

Week 7: Artificial Neural Networks (ANNs)

  • Fundamentals of ANNs and their applications
  • Reading Material:
    • Chapter 6: “Artificial Neural Networks” from Artificial Intelligence: A Modern Approach
  • Assignment: Implement a basic neural network model.
  • Lab Work: Experiment with neural network frameworks in Python.
  • Lab Assignment: Train and test a neural network on a given dataset.

Week 8: Natural Language Processing (NLP)

  • Introduction to NLP techniques and applications
  • Reading Material:
    • Chapter 7: “Natural Language Processing” from Artificial Intelligence: A Modern Approach
  • Assignment: Apply NLP techniques to text data.
  • Lab Work: Implement basic NLP tasks using Python libraries.
  • Lab Assignment: Develop a text classification or sentiment analysis application.

Week 9: Recent Trends in AI

  • Overview of recent developments and applications in AI
  • Reading Material:
    • Review recent research papers and articles on current AI trends
  • Assignment: Research and present a recent AI development or application.
  • Lab Work: Explore recent AI tools and technologies.
  • Lab Assignment: Implement a project using a recent AI technology.

Week 10: Review and Project Work

  • Review of key concepts covered in the course
  • Assignment: Complete and finalize the semester project.
  • Lab Work: Continue development of the semester project.
  • Lab Assignment: Prepare a project report and presentation.

Week 11: Project Presentations

  • Presentation of semester projects
  • Assignment: Deliver a presentation of the semester project.
  • Lab Work: Present final projects and participate in peer reviews.
  • Lab Assignment: Submit the final project report and presentation slides.

Week 12: Final Exam and Course Wrap-Up

  • Comprehensive review of the course material and final exam
  • Assignment: Complete any outstanding assignments and submit.
  • Lab Work: Participate in a review session and complete the final exam.
  • Lab Assignment: Finalize and submit any remaining coursework.

Grading Distribution:

  • Quizzes (10%): Regular quizzes to assess understanding of key concepts.
  • Assignments (20%): Weekly assignments based on lecture and reading materials.
  • Lab Work (20%): Practical lab exercises and assignments.
  • Project (20%): Semester project including implementation, report, and presentation.
  • Final Exam (30%): Comprehensive exam covering the entire course.

Following is the list of semester project sorted in your roll number sequence. For an example if your roll number is 3, you have to choose “Sentiment Analysis Tool” as your semester project of AI.

  1. Chatbot for Customer Service: Develop a chatbot using natural language processing to handle customer queries.
  2. Recommendation System: Build a recommendation system for products or movies using collaborative filtering.
  3. Sentiment Analysis Tool: Create a tool to analyze the sentiment of social media posts or customer reviews.
  4. Spam Email Classifier: Implement a classifier to detect and filter out spam emails.
  5. Image Classification Using CNN: Develop a convolutional neural network (CNN) to classify images from a dataset.
  6. Speech Recognition System: Create a system to convert spoken language into text.
  7. Predictive Text Input System: Build a system that predicts the next word or phrase based on user input.
  8. AI-Based Game Player: Design an AI agent to play a specific game using algorithms like Minimax or Q-learning.
  9. Fraud Detection System: Implement a system to detect fraudulent transactions in financial data.
  10. AI-Powered Personal Assistant: Develop a virtual personal assistant capable of managing schedules, reminders, and tasks.
  11. Facial Recognition System: Create a facial recognition system to identify individuals from images.
  12. Medical Diagnosis Assistant: Build an AI tool to assist in diagnosing medical conditions from symptoms.
  13. Autonomous Vehicle Navigation: Design an AI system for navigating an autonomous vehicle through a simulated environment.
  14. Voice-Activated Home Automation: Develop a voice-controlled system for automating home devices.
  15. AI-Based Stock Market Predictor: Implement a model to predict stock market trends using historical data.
  16. Text Summarization Tool: Create a tool that summarizes long texts into shorter, more digestible summaries.
  17. Handwriting Recognition System: Build a system to recognize and convert handwritten text into digital text.
  18. AI-Powered Financial Advisor: Develop an AI tool to provide financial advice based on user inputs and market data.
  19. Natural Language Generation for Reports: Create a system that generates reports or summaries from structured data.
  20. Disease Prediction Model: Implement a model to predict the likelihood of diseases based on patient data.
  21. AI-Based Language Translator: Build a tool for translating text between different languages using neural networks.
  22. Traffic Sign Recognition System: Develop a system to recognize and interpret traffic signs from images.
  23. AI for Music Generation: Create an AI system that generates original music compositions.
  24. Emotion Recognition from Text: Implement a tool to detect emotions in written text.
  25. Automated Essay Scoring System: Design an AI system to grade essays based on content and structure.
  26. Personalized Learning System: Develop an AI tool that customizes learning materials based on student performance.
  27. AI-Based Content Moderation: Create a system for automatically moderating user-generated content on platforms.
  28. Financial Forecasting Model: Implement a model to forecast financial trends based on historical data.
  29. AI-Enhanced E-Commerce Search: Develop an AI-enhanced search engine for e-commerce websites to improve product search results.
  30. Smart Inventory Management System: Create an AI system for managing and predicting inventory needs.
  31. AI for Art Generation: Build a tool that generates digital art using neural networks.
  32. Virtual Reality with AI: Develop an AI system for enhancing virtual reality experiences with interactive elements.
  33. AI for Real Estate Valuation: Implement a model to estimate real estate property values based on various features.
  34. Personalized Fitness Coach: Create an AI-powered fitness coach that suggests workout routines based on user data.
  35. AI-Driven Chatbot for Mental Health: Build a chatbot that provides mental health support and advice.
  36. Automated Customer Feedback Analysis: Develop a system to analyze and categorize customer feedback.
  37. AI for Crime Prediction: Implement a model to predict crime occurrences based on historical data.
  38. Voice-to-Text Transcription Service: Create a service that transcribes voice recordings into text.
  39. AI-Based Resume Screening: Develop an AI tool to screen and rank resumes for job applications.
  40. Energy Consumption Optimization: Build an AI system to optimize energy consumption in buildings.
  41. AI for Sports Analytics: Create a tool that analyzes sports performance data and provides insights.
  42. AI-Powered Travel Planner: Develop a system that plans travel itineraries based on user preferences and constraints.
  43. Intelligent Tutoring System: Build an AI tutor that provides personalized assistance in various subjects.
  44. AI-Based Financial Risk Assessment: Implement a tool to assess financial risks based on market data.
  45. Smart Chatbot for E-Learning: Create a chatbot that assists with online learning by answering questions and providing resources.
  46. AI for Real-Time Translation in Videos: Develop a system for translating spoken language in videos in real-time.
  47. AI-Powered Job Matching System: Build a system that matches job seekers with job openings based on their profiles.
  48. Automated News Generation: Create an AI tool that generates news articles from data sources.
  49. AI for Predictive Maintenance: Develop a system that predicts equipment failures before they occur.
  50. AI-Driven Fashion Recommendation System: Build a tool that recommends fashion items based on user preferences and trends.
Scroll to Top