Mark Humphrys - Teaching - CA300


Search:   Help on Search


Introduction to Artificial Intelligence



How to contact me

I prefer not to receive first contact by email. See What I think about email.

See How to contact me.



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. Continuum of Autonomy
    7. 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. Advanced Topics in Machine Evolution

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


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


  5. MAYBE NOT ON COURSE THIS YEAR - Philosophy of AI
    1. Philosophy of AI
    2. Philosophy and Future of AI

    3. What is Intelligence?
    4. What is Consciousness?
    5. What is Life?



Concepts



Practical

Practical

Deadline Fri 11 Dec 2009.




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