Home ] Up ]

 

Areas for Exam 1 Questions (10 questions will be selected):

  1. Be prepared to summarize the basic advantages and disadvantages of: fuzzy vs neural network systems, conventional vs neural network signal processing, and/or conventional vs fuzzy expert systems.

  2. Be prepared to to set up a linear and nonlinear dynamic system using state and output equations (identifying states, inputs, and outputs). 

  3. Systems terminology: know the difference between linear vs nonlinear, dynamic vs static/quasi-static, and/or deterministic vs stochastic.

  4. Controls Terminology:  Be prepared to state the advantages-disadvantages of feedback vs feedforward neurocontrol, linear vs adaptive control, and/or linear vs fuzzy control.

  5. Know the following "fuzzy" terminology: fuzzy sets (e.g., vs crisp, universe of discourse, membership function, basic properties and math), fuzzy relations and inference.

  6. Be able to describe the Mamdani and Suguni fuzzy inference system structures, and how they differ.

  7. Be able to describe how you would set up a Mamdani system, using GFIE, given linguistic problem description.

  8. Be able to graphically go through the process of Mamdani inference for a specific expert system example, from inputs to output.

  9. Be able to identify and give mathematically 2 approaches for "and" 'or" "implication" aggregation" and "defuzzify" (this includes solving for a centroid).

  10. Be able to describe how you would set up a fuzzy control system, and why such a system may have some advantages over a conventional control system.  Give an example.

  11. Be able to describe, with a concrete example, how changes in an internal parameter (e.g., membership function parameter) or the assumed type of operation (e.g., "and") affected fuzzy system performance.

  12. Be able to map between a "rule table" to linguistic description of rules. 

  13. Be able to describe the basic anatomy and physiology of a neuron, basic neuromuscular terms (Table E), structural organization of the brain (Table F), and/or basic pathology of key diseases (Table J).  Expect several short parts to this question.

Areas for Exam II Questions (10 will be selected, 9 of which are from the following list):
  1. Mathematically describe the classic artificial "neuron" processing element, including both the input "integration" function and the activation (transfer) function (give for a "solf saturating" sigmoid).  Given three inputs (on <0,1>, determine the output.

  2. The classic unsupervised approach for ANN learning is Hebbian.  Describe and give the mathematics for the special variant of a "forgetting" term, then one other of your choice.  How does it differ from the Delta rule?

  3. Given a feedforward net, give and be able to apply the classic backprop learning algorithm for an internal neuron (both the forward (action) net and backprop (e.g., see Fig 10.8)

  4. Set up a neural net structure that can be used to solve a small Sugino fuzzy inference system where some of the ANNs use radial basis function "receptive fields." (e.g., see Fig 9.10).  Give the conditions under which an RBFN & FIS are functionally equivalent (e.g., see p. 242). 

  5. Draw a block diagram structure for a neural network model reference controller and plant, and then describe how you would go about setting up plant identification and controller training using Matlab (e.g., what parameters are needed for the controller training algorithm?)

  6. What is reinforcement learning, and why is implementation so challenging?  Carefully delineate it from supervised learning, and then describe several of the key approaches.

  7. Draw the basic Cerebellar circuit, and using it, discuss how it might learn to recognize patterns (e.g., ideas of Marr, Albus, etc).

  8. One of the three topics we discussed related to Houk et al.

  9. What are the classic steps for setting up and using a genetic algorithm?

  10. Describe the protocol for gradient-free optimization, and then describe a structure for applying it to the use of GA's for neuro-fuzzy control.