Next: Programming
Up: Course Information
Previous: Assessment
- Introduction -- General Course Info, AI Basics: AI systems,
definitions, Relation to other courses especially last years AI I.
- AI Revision -- Summary of key concepts taught last year and
examples of their use in this course.
- Knowledge Representation -- Representation approaches, Issues,
Granularity.
- Knowledge Representation -- Rules and predicate logic, Semantic
Nets and Frames: Weak slot and filler structures.
- Knowledge Representation -- Strong slot and filler structures:
Conceptual dependency, scripts, CYC.
- Reasoning with Uncertainty -- Non-monotonic reasoning, problem
solving.
- Statistical Reasoning -- Bayes Theorem, Certainty Factors,
Bayesian Networks, Dempster Schafer Theory, Belief Models, Fuzzy models.
7
- Parallel and Distributed Reasoning -- Psychological modelling,
Architectures, Blackboards.
- Planning -- Blocks world review, Components of a planning system,
Goal stack planning.
- Planning -- Non linear planning, Constraint posting, Hierarchical
planning, Reactive systems.
- Understanding -- What is understanding?, Why is it hard?,
Understanding as constraint satisfaction.
- Learning -- What is learning?, Learning from advice, Learning in
problem solving.
- Learning -- Learning from example, discovery and analogy. Genetic
algorithms and Neural networks.
- Common Sense -- Qualitative physics, Common sense Ontologies, Memory
organisation.
14
- Vision -- Image formation, describing images: surfaces, edges
etc., 3D object modelling.
- Vision -- Line labelling, Relaxation labelling.
- Vision -- Object recognition, Template matching, Extended Gaussian
images.
- Vision -- Object recognition: Model based matching - tree, graph
searching and labelling methods.
dave@cs.cf.ac.uk