1 / 26

Revision Michael J. Watts mike.watts.nz

Revision Michael J. Watts http://mike.watts.net.nz. Lecture Outline. Overview of course material. Introduction to AI. Artificial / Computational Intelligence CI models. Data Transformation. Statistical operations on Data Data transformations The objectives of a data transform

emilie
Download Presentation

Revision Michael J. Watts mike.watts.nz

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Revision Michael J. Watts http://mike.watts.net.nz

  2. Lecture Outline Overview of course material

  3. Introduction to AI Artificial / Computational Intelligence CI models

  4. Data Transformation Statistical operations on Data Data transformations The objectives of a data transform Linear versus non-linear transformations Transformations for pre-processing of data DFT and FFT Transformations Wavelet Transformations

  5. Rule Based Systems Production systems Facts & Templates Production rules The inference process Advantages of production systems Disadvantages of production systems Expert systems

  6. Fuzzy Sets and Fuzzification Crisp sets Fuzzy sets Fuzzy membership functions Fuzzification Fuzzy logic

  7. Fuzzy Rules, Inference and Defuzzification Fuzzy rules Fuzzy inference Defuzzification

  8. Fuzzy Systems Fuzzy systems Developing fuzzy systems Advantages of fuzzy systems Disadvantages of fuzzy systems

  9. Applications of Fuzzy Systems Advantages of fuzzy systems Pattern recognition / Classification Fuzzy control Decision making

  10. Biological and Artificial Neurons Biological Neurons Biological Neural Networks Artificial Neurons Artificial Neural Networks

  11. Perceptrons Perceptron architecture Perceptron learning Problems with perceptrons

  12. Multi-Layer Perceptrons Multi-Layer Perceptrons Terminology Advantages Problems

  13. Backpropagation Training Backpropagation training Error calculation Error surface Pattern vs. Batch mode training Restrictions of backprop Problems with backprop

  14. Kohonen Self Organising Maps Vector Quantisation Unsupervised learning Kohonen Self Organising Topological Maps

  15. Applying Neural Networks When to use an ANN Preparing the data Apportioning data What kind of ANN to use Training ANN

  16. Evolution What is evolution? What evolution is not Lamarckian evolution Mendellian genetics Darwinian evolution

  17. Genetic Algorithms Genetic algorithms Jargon Advantages of GAs Disadvantages of GAs Simple genetic algorithm Encoding schemata Fitness evaluation

  18. Genetic Algorithms Selection Creating new solutions Crossover Mutation Replacement strategies Word matching example

  19. Evolution StrategiesEvolutionary ProgrammingGenetic Programming Evolution Strategies Evolutionary Programming Genetic Programming

  20. Applications of Evolutionary Algorithms Advantages of EA EA Application areas Scheduling Load balancing Engineering Path Planning

  21. Evolutionary Algorithms and Neural Networks Problems with ANN EA and ANNs ANN Topology Selection by EA Initial Weight Selection Selecting Control Parameters EA Training

  22. Evolutionary Algorithms and Fuzzy Systems Advantages of fuzzy systems Problems with fuzzy systems Applying EA to fuzzy systems Optimisation of MF Optimisation of rules Optimisation of fuzzy systems

  23. IIS for Speech Processing Speech Production Speech Segments Speech Data Capture Representing Speech Data Speech Processing Speech Recognition

  24. IIS for Bioinformatics What is bioinformatics? What is DNA? How is it processed in cells? What is DNA data? How is DNA data represented? How can IS be applied to DNA data?

  25. IIS for Finance Economic data Applications Why is it hard? Methods to use Applications of IIS

  26. IIS for Image Processing What are images? Why process them? What is Image Processing/Recognition?

More Related