Course Objectives

The objectives of this course are to:

  1. Introduce the foundational principles and techniques of Artificial Intelligence.
  2. Explore intelligent agents, their architectures, and applications.
  3. Provide practical experience in implementing AI algorithms and techniques.
  4. Examine search strategies and problem-solving methods in AI.
  5. Teach knowledge representation techniques and their applications.
  6. Explore natural language processing and its practical use cases.
  7. Analyze AI programming languages and their roles in developing expert systems.
  8. Develop an understanding of AI's ethical considerations and potential applications.

Learning Outcomes

By the end of this course, students should be able to:

  1. Explain the fundamentals, goals, types, techniques, and tools of AI.
  2. Discuss intelligent agents, their characteristics, environments, and architectures.
  3. Describe the Turing test, the "Chinese Room" experiment, and the differences between optimal and human-like reasoning.
  4. Analyze heuristic trade-offs in terms of completeness, optimality, time complexity, and space complexity.
  5. Apply AI search algorithms and solve combinatorial problems.
  6. Represent knowledge using semantic networks, frames, and predicate logic.
  7. Implement practical NLP solutions, including sentiment analysis, machine translation, and chatbots.
  8. Evaluate AI programming languages and develop applications for expert systems.
  9. Build and test AI-based projects, including robotics and intelligent simulations.

Detailed Course Content

Module 1: Introduction to Artificial Intelligence

  • Overview of AI
  • History, goals, and types of AI
  • AI techniques, branches, and applications

Module 2: Intelligent Agents

  • Concepts and examples of agents
  • Agent faculties and rationality
  • Agent environments and architectures

Module 3: Search in AI

  • General classes of AI search problems
  • Problem-solving using search algorithms
  • Types of search techniques and their applications
  • Combinatorial explosion and its consequences

Module 4: Knowledge Representation

  • Knowledge representation techniques: predicate logic, non-monotonic logic, probabilistic reasoning
  • Semantic networks: types, relationships, and inheritance
  • Frames: components and applications

Module 5: Natural Language Processing (NLP)

  • Syntactic and semantic structures
  • NLP applications: sentiment analysis, machine translation, and question answering

Module 6: Expert Systems and AI Programming

  • Characteristics and components of expert systems
  • Programming languages for AI: Prolog, LISP, Python
  • Applications in image recognition and robotics

Module 7: AI Applications and Ethics

  • Practical applications in robotics and intelligent systems
  • Ethical considerations in AI: data privacy and bias

Lab Work and Practical Exercises

  1. Turing Test Simulation: Conduct a practical version of the Turing test.
  2. NLP Applications: Implement sentiment analysis, spam detection, and chatbot development.
  3. Search Algorithm Simulations: Solve the "Missionaries and Cannibals" problem using search techniques.
  4. Agent Simulation: Model ant colony foraging or bird flocking behavior.
  5. Robotics: Design and build a simple robot, such as a lawn-trimming robot.
  6. Image Recognition and Machine Learning: Implement facial recognition algorithms.
  7. Group Projects: Collaborative tasks involving AI applications in various domains.

Teaching/Learning Methods

  • Lectures and multimedia presentations
  • Group discussions and seminars
  • Hands-on lab exercises and simulations
  • Case studies of AI applications
  • Group projects and collaborative problem-solving

Modes of Assessment

  1. Continuous Assessment (quizzes, assignments, lab participation): 50%
  2. Final Examination: 50%

Reading List/References

Primary Texts (Essential Readings):

  1. Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach. 4th Edition. Pearson.
  2. Poole, D., Mackworth, A., & Goebel, R. (2021). Computational Intelligence: A Logical Approach. Oxford University Press.

Supplementary Texts (Recommended Readings):

  1. Charniak, E. (2022). Introduction to Artificial Intelligence. Addison-Wesley.
  2. Dean, T., & Wellman, M. P. (2020). Planning and Control in Artificial Intelligence. Morgan Kaufmann.

Online Resources:

  1. AI Algorithms Tutorials: https://www.tutorialspoint.com/ai
  2. NLP Applications: https://www.nlp.stanford.edu
  3. OpenAI Research Papers: https://openai.com/research