1. Using the type of numerical maths we use to describe the physical world: e.g., the Brain
2. Knowledge Engineer:
3. work out what the client wants/needs - - work out how to represent it (choose best KRL) -Create rule/fact base and (try to) verify it is complete and accurate and will finish - Discuss with client
4. Probabilistic reasoning e.g. Bayesian networks
5. To build models: 1. Use graphs/ Dependency Arcs to indicate conditional probabilities - creates structure of model 2. Measure frequencies of events - provides parameters of model
6. To use Models: Combine probabilities to make predictions: - independent events=>multiply -dependent events=>apply Bayes Rule
7. Artificial Neural Networks
8. Logical calculus -inputs and bias(1) -weights on links -1,0,+1 -output 1 if sum of inputs >0
9. Link to KRL -single node does And/OR/NOT -can compute any logical function - by suitable combination of units -have to be hand designed
10. Perceptron
11. simple update rule: -change in weight on link = error*signal*learning rate
12. - will learn any linearly separable problem - can't learn non-separable problems e.g. XOR
13. Multi-Layer perceptron
14. 1. Signals feed-forward to make predictions using sigmoid function 2. During training errors propagated backwards -compare output to desired output apply perceptron update rule -send errors backwards in proportion to signal through links
15. Machine Learning Engineer
16. Unsupervised e.g. clustering
17. Supervised learning: model building
18. - training (used to guide search process ) - validation (used to avoid overfitting) - test (used to estimate accuracy )
19. ML algorithms are: 1 A way of representing decision boundaries e.g. rules, set of examples examples 2. A search algorithm for moving/improving/learning them e.g. hill climbing, EAs...
20. do we know what the outputs should be?
21. In order to learn from experience and generalise to new inputs
22. syntax: how you write it down
23. interpretation:what does it mean in this context
24. semantics:what symbols mean
25. Using formal models of logic: the Mind
26. Knowledge Representation Languages
27. the current state of the world- "facts" (inputs)
28. how the world works (model) - "rules" applying to things - metaknowledge/ontologies applying to groups of things or relationships
29. how these can be manipulated( what form of logic)
30. Expressive (can say what we need to)
31. Effective (can infer what we need to)
32. Explicit (can justify inferences
33. In order to do Inference: Create new facts (output)
34. Depend on the type of logic allowed
35. Propositional logic - BIVALENT (everything is T/F), - Implies, IsEquivalent to , AND, OR, NOT Sound, Complete, Decidable, Not Expressive
36. First order logic: Adds variables, existential/universal quantifiers Sound, expressive, not decidable
37. Fuzzy Logic Multivalent (Things can belong to more than one class)
38. 2. Calculate inferences for each fuzzy rule that applies
39. Expert systems
40. Semantic Web, e.g., RDF, XML self-describing data, AIML - separate facts from details about how languages work
