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
- Introduction to AI
- Introduction to AI
- Survey of AI
- AI Links
- Robotics Links
- Evolution Links
- Philosophy of AI
- Philosophy and Future of AI
- What is Intelligence?
- What is Consciousness?
- What is Life?
- Continuum of Autonomy
- History of AI
- Machine Learning (mainly focusing here on Neural Networks)
- Search
- Maximising a function
- Machine Learning
- Chaotic functions
- Chaos Theory demo
- Single-layer Neural Networks
- Multi-layer Neural Networks
- Continuous Output - The sigmoid function
- Notation [REFERENCE]
- Back-propagation [MULTI-LAYER LEARNING RULE]
- The Back-propagation algorithm [REFERENCE]
- Designing the Inputs
- Infinite weights/thresholds are bad
- Specialisation
- Alternatives to Supervised Learning
- Sample code for Neural Networks
- Neural Net Exercise - Binary Encoder Network
- Neural Net Exercise - X and O recogniser
- Machine Learning - Reference
- Machine Evolution (mainly focusing here on Genetic Algorithms)
- Computational Evolution
- The Genetic Algorithm [HEURISTIC]
- Reproduction
- Boltzmann "soft max" distribution
- GAs - Discussion
- What is Life?
- Sample code for Genetic Algorithms
- How to make a decision probabilistically
- GA Exercise - Adaptive Landscape
- Computational Evolution - Reference
- General
- Comparison of Neural Net and GA
- Continuum of Autonomy
- Open Issues in AI
- NOT ON COURSE THIS YEAR
- Advanced Topics in Machine Evolution
- Architectures of Autonomous Agents
Concepts
- Search and Learning - state spaces,
generalisation, nearest-neighbours.
- Learning from examples - Single-layer Neural Networks,
Multi-layer Neural Networks, supervised learning, back-propagation,
Neural Networks as generalisations (of state-spaces or non-linear functions).
- Learning from rewards - Reinforcement Learning, Delayed reinforcement,
Markov worlds, exploration v. exploitation, world models.
- Artificial evolution - fitness landscapes, hill-climbing, the Genetic Algorithm,
classifier systems, Genetic Programming.
- Collective behavior - Cellular Automata, Chaos and Complexity, basins and attractors,
prediction, the Game of Life, Artificial Life.
Practical
Practical
Deadline Fri 19 Dec 2008.
- Coverage of both the
symbolic and the biological approaches to AI
in one book:
- Neural Networks:
-
Neural Computing,
Philip D. Wasserman, 1989.
- Library 006.3.WAS.
-
Neural Network Architectures: An Introduction,
Judith Dayhoff, 1990.
- Library 006.3.DAY.
-
An Introduction to Neural Computing,
Igor Aleksander and Helen Morton, 2nd edn, 1995.
- Library 006.3.ALE.
-
"Learning Internal Representations by Error Propagation",
Rumelhart et al,
Chapter 8 in Parallel Distributed Processing,
Rumelhart and McClelland,
1986.
- Library 153.RUM.
- Genetic Algorithms:
-
Genetic Algorithms in Search, Optimization and Machine Learning,
David Goldberg, 1989.
- Library 006.31.GOL.
Library categories
- 006 - Special computer methods
- 006.3 - Artificial Intelligence
- 629 - Other branches of engineering
- 629.8 - Automatic control engineering (robotics)
- 100 - Philosophy and psychology
- 120 - Epistemology, causation, humankind
- 150 - Psychology
- 153 - Mental processes and intelligence
