Mark Humphrys - Teaching - CA300


Search:   Help on Search

Introduction to Artificial Intelligence

Email

With several hundred students, I WOULD PREFER NOT TO RECEIVE COMMUNICATION BY EMAIL. See How to contact me. See What I think about email.

Course Descriptor

Notes

  1. Introduction to AI
    1. Introduction to AI
    2. Survey of AI
    3. AI Links
    4. Robotics Links
    5. Evolution Links

    6. Philosophy of AI
    7. Philosophy and Future of AI

    8. What is Intelligence?
    9. What is Consciousness?
    10. What is Life?

    11. Continuum of Autonomy
    12. History of AI


  2. Machine Learning (mainly focusing here on Neural Networks)
    1. Search
    2. Maximising a function

    3. Machine Learning

    4. Chaotic functions
    5. Chaos Theory demo

    6. Single-layer Neural Networks
    7. Multi-layer Neural Networks
    8. Continuous Output - The sigmoid function
    9. Notation [REFERENCE]

    10. Back-propagation [MULTI-LAYER LEARNING RULE]
    11. The Back-propagation algorithm [REFERENCE]
    12. Designing the Inputs
    13. Infinite weights/thresholds are bad
    14. Specialisation
    15. Alternatives to Supervised Learning

    16. Sample code for Neural Networks
    17. Neural Net Exercise - Binary Encoder Network
    18. Neural Net Exercise - X and O recogniser
    19. Machine Learning - Reference


  3. Machine Evolution (mainly focusing here on Genetic Algorithms)
    1. Computational Evolution
    2. The Genetic Algorithm [HEURISTIC]
    3. Reproduction
    4. Boltzmann "soft max" distribution
    5. GAs - Discussion

    6. What is Life?
    7. Sample code for Genetic Algorithms
    8. How to make a decision probabilistically
    9. GA Exercise - Adaptive Landscape
    10. Computational Evolution - Reference


  4. General
    1. Comparison of Neural Net and GA
    2. Continuum of Autonomy
    3. Open Issues in AI


  5. NOT ON COURSE THIS YEAR
    1. Advanced Topics in Machine Evolution
    2. Architectures of Autonomous Agents

Concepts

Practical

Practical - Not yet ready to launch.

Recommended Reading

  1. Coverage of both the symbolic and the biological approaches to AI in one book:

  2. Neural Networks:

  3. Genetic Algorithms:

Library categories