Bull-Paper Review1 - PowerPoint PPT Presentation

About This Presentation
Title:

Bull-Paper Review1

Description:

... between ZCS and XCS: The most significant difference between XCS and other ... Problems Review of Popular Search Techniques (Search1, Search2, Search3, Search ... – PowerPoint PPT presentation

Number of Views:29
Avg rating:3.0/5.0
Slides: 5
Provided by: ricardo125
Learn more at: https://www2.cs.uh.edu
Category:
Tags: bull | most | paper | popular | review1 | search

less

Transcript and Presenter's Notes

Title: Bull-Paper Review1


1
Bull-Paper Review1
  1. Holland (1986) Classifier systems rule-based
    systems with general mechanisms to process rules
    in parallel, for the adaptive generation of
    rules, and for testing the effectiveness of
    existing rules.
  2. LCS Reinforcement Learning ? Evolutionary
    Computing ? heuristics to produce adaptive
    systems
  3. Bull on EC the population of candidate
    solutions is seen to adapt to the problem
  4. Reinforcement learning attempts to map state
    action combinations to their utility, with the
    aim to maximize future rewards.
  5. EC is used to search the space of possible rules,
    while reinforcement learning techniques are used
    to assign utilities to existing rules, thereby
    guiding the search for better rules.

2
Bull-Paper Review2
  1. Hollands LCS bids of successfully rules are
    placed in a placed in a bucket and reinforcement
    learning redistributes these bids between
    subsequent chosen rules. As an example how this
    redistribution is done for ZCS read pages 20-21
    of the textbook.
  2. For understanding ZCS read the textbook and not
    Bulls paper who fails to explain its mechanisms
    clearly.
  3. Bull on the difference between ZCS and XCS The
    most significant difference between XCS and other
    systems it its intention to form an accurate
    mapping of the problem space.
  4. ZCS/Holland employ TD(0) whereas XCS employs
    Q-learning ?to be explained next week when
  5. The second paragraph of the textbook on page 124
    assumes a more complex model of XCS in which a
    state space will be explored ?to be explained
    next week as of now, just assume that the payoff
    of an action is the reward it receives PR

3
Bull-Paper Review3
  • Bulls characterization how deletion works in XCS
    is misleading in that is suggest as is the only
    thing usedmost implementation use as/F, as
    suggested earlier
  • Different variations of LCS differ in to which
    sets of rules operations are applied
  • N all rules (also sometimes called P)
  • M rules that match the input message
  • A rule(s) that are selected to process the
    incoming message
  • Application of LCS-style systems (mostly in
    optimization, control, and modelingI am not
    convinced they are too many applications in data
    mining except mining data streams)
  • Stock price forecasting
  • Fighter aircraft modeling
  • Control of routing nodes in package switch
    networks
  • Control in electrical power distribution
  • Traffic Signal Control

4
Final Exam Review
  • Quiz2 2008 Review List for COSC 6367 Quiz2 is
    scheduled for Th., March 27, 230p and will be
    "open everything" at least 80 of the material
    covered in Quiz1 will center on material that was
    covered in the COSC 6367 lectures. The material
    relevant for Quiz2 includes
  • Bull Paper
  • Relevant Textbook pages 71-84, 115-142, 153-164,
    173-182
  • 2) Transparencies Overview ES Eiben Chapter4
    Evolution Strategies On Numerical Optimization
    Problems Review of Popular Search Techniques
    (Search1, Search2, Search3, Search
  • Dr. Eick's Introduction to Machine Learning with
    EC XCS Tutorial by Stewart Wilson (in ps-format)
  • Eiben Chapter8 Parameter Control Eiben Chapter9
    (Spatial Considerations) Eiben Chapter10 (Memetic
    Alg.)---partially(see book pages above)
Write a Comment
User Comments (0)
About PowerShow.com