Artificial Intelligence Lab

Course Information

  • Semester: 6th
  • Course Code: 07-0619-AI Lab609
  • Credits: 01
  • Course Teacher: Md Habibul Basar Faruq
  • Email: mh.faruq06@gmail.com

Lab Objectives

Upon completion of this lab, students will be able to:

  • Implement fundamental AI algorithms including search, CSP, and Markov Decision Processes
  • Develop reinforcement learning agents using Q-learning and policy iteration
  • Build and train simple machine learning models including classifiers and regressors
  • Construct and train neural networks using backpropagation
  • Apply probabilistic inference in Bayesian networks
  • Develop AI applications for real-world problems and game environments
  • Use AI programming tools and libraries such as Python, TensorFlow, and PyTorch

Weekly Lab Activities

  • Week 1: Lab Setup and Environment

    • Install Python, Jupyter Notebooks, and required libraries
    • Introduction to Git and version control
    • Overview of AI Lab goals and workflow

  • Week 2: Search Algorithms

    • Implement Breadth-First Search (BFS) and Depth-First Search (DFS)
    • Introduce heuristic search with A* algorithm

  • Week 3: Constraint Satisfaction Problems (CSP)

    • Backtracking algorithm for CSP
    • Implement heuristics to improve CSP solving

  • Week 4: Markov Decision Processes (MDPs)

    • Implement value iteration and policy iteration algorithms

  • Week 5: Reinforcement Learning Basics

    • Q-learning algorithm
    • Policy updates and exploration strategies

  • Week 6: Machine Learning I

    • Implement simple classifiers (e.g., k-NN, decision trees)
    • Perform regression analysis

  • Week 7: Neural Networks I

    • Build simple feedforward neural networks
    • Implement forward propagation

  • Week 8: Neural Networks II

    • Implement backpropagation algorithm
    • Train networks on sample datasets

  • Week 9: Probabilistic Graphical Models

    • Introduction to Bayesian networks
    • Implement inference algorithms

  • Week 10: Natural Language Processing Basics

    • Text preprocessing and tokenization
    • Simple NLP pipeline creation

  • Week 11: Project Proposal and Design

    • Form project teams
    • Choose AI applications for project work

  • Weeks 12-14: Project Development

    • Implement, test, and debug AI projects
    • Apply multiple AI techniques as needed

  • Week 15: Project Presentation and Evaluation

    • Demonstrate final projects
    • Submit reports and reflect on performance

Assessment Components

  • Weekly coding assignments and lab reports – 40%
  • Lab participation and attendance – 10%
  • Mid-term project checkpoint – 10%
  • Final project implementation – 30%
  • Project presentation and final report – 10%

References and Resources

  • Artificial Intelligence: A Modern Approach – Russell & Norvig
  • Deep Learning – Goodfellow, Bengio, and Courville
  • Online tutorials: TensorFlow, PyTorch
  • Course slides and materials will be provided during sessions