SlideShare ist ein Scribd-Unternehmen logo
1 von 43
Downloaden Sie, um offline zu lesen
Final Presentation INF/SCR-06-54
                                                       Applied Computing Science, ICS




            A Comparison of Evaluation
                Methods in Coevolution


                               Ting-Shuo Yo

                        Supervisor: Edwin D. de Jong
                                   Arno P.J.M. Siebes
Outline

●   Introduction
●   Evaluation methods in coevolution
●   Performance measures
●   Test problems
●   Results and discussion
●   Concluding remarks
Introduction

●   Evolutionary computation
●   Coevolution
●   Coevolution for test-based problems
●   Motivation of this study
Genetic Algorithm
Initialization



                       2. SELECTION           Parents

  1. EVALUATION
                                      3. REPRODUCTION
         Population                      (crossover, mutation,...)


                 4. REPLACEMENT
                                             Offspring
   While (not TERMINATE)


                                  TERMINATE
                                                                End
Coevolution
Initialization


                          1. EVALUATION



                             ................
       Subpopulation                            Subpopulation
        2. SELECTION                            2. SELECTION
        3. REPRODUCTION                         3. REPRODUCTION
        4. REPLACEMENT                          4. REPLACEMENT



                      While (not TERMINATE)



                                       TERMINATE
                                                                  End
Test-Based Problems
f(x)
                 original function

                 regression curve                               s1
                                                                s2
                                                                 s3




                                                                      x
       t1   t2      t3      t4       t5   t6   t7   t8   t9   t10
Coevolution for Test-Based Problems

         Test           1. EVALUATION
       population       Interaction:
     2. SELECTION        ●   Does the solution solve the
     3. REPRODUCTION         test?
     4. REPLACEMENT      ●   How good does the solution
                             perform on the test?

       Solution
      population        Solutions: the more tests it
                          solves the better.
      2. SELECTION
      3. REPRODUCTION   Tests: the less solutions pass it
      4. REPLACEMENT      the better.
Motivation

●   Coevolution provides a way to select tests
    adaptively → stability and efficiency
●   Solution concept → stability
●   Efficiency depends on selection and
    evaluation.
●   Compared to evaluation based on all relevant
    information, how do different coevolutionary
    evaluation methods perform?
Concepts for Coevolutionary
            Evaluation Methods

●   Interaction
●   Distinction and informativeness
●   Dominance and multi-objective approach
Interaction
●   A function that returns the outcome of interaction
    between two individuals from different
    subpopulations.
    –   Checkers players: which one wins
    –   Test / Solution: if the solution succeeds in solving the
        test                             S 1 S 2 S 3 S 4 S 5 sum
                                   T1   0   1    0   0    1   2
                                   T2   0   0    1   1    0   2
●   Interaction matrix             T3   0   1    1   0    0   2
                                   T4   1   0    0   0    0   1
                                   T5   1   0    1   0    0   2
                                  sum   2   2    3   1    1
Distinction
                   Solutions                                 T3
              S1   S2   S3   S4   S5   sum         S1   S2   S3   S4   S5 sum
      T1      0     1    0    0    1   2     S1    -     0    0    0    0
      T2      0     0    1    1    0   2     S2    1     -    0    1    1
Test  T3      0     1    1    0    0   2     S3    1     0    -    1    1
cases T4      1     0    0    0    0   1     S4    0     0    0    -    0
      T5      1     0    1    0    0   2     S5    0     0    0    0    -
        sum   2     2    3    1    1         sum   2     0    0    2    2 6

●   Ability to keep diversity on the other subpopulation.
●   Informativeness
Dominance and MO approach
    f2

                      non-dominated
                                           S1 is dominated by S2 iff:
                      dominated




                                      f1



●        Keep the best for each objective.
●        MO: number of individuals that dominate it
Evaluation Methods

●   AS: Averaged Score
●   WS: Weighted Score
●   AI: Averaged Informativeness
●   WI: Weighted Informativeness
●   MO
AS and WS
●       AS : (# positive interaction) / (# all interaction)
                                   Solutions
                            S1    S2 S3 S4 S5 sum
                      T1    0      1 0 0 1 2              0.4
                      T2    0      0 1 1 0 2              0.4
                Test  T3    0      1 1 0 0 2              0.4
                cases T4    1      0 0 0 0 1              0.2
                      T5    1      0 1 0 0 2              0.4
                      sum   2      2 3 1 1
                            0.4   0.4   0.6   0.2   0.2

    ●   WS : each interaction is weighted differently.
AI and WI
●   AI : # of distinctions it makes
●   WI : each distinction is weighted differently.
           S1>S2 S1>S3 S1>S4 S1>S5 .............
      T1     1     1     0     1        ....                                5
      T2     0     0     0     1        ....                                2
      T3     1     1     0     0        ....                                6
      T4     0     1     0     1        ....                                2
      T5     0     0     0     0        ....                                1

     In the algorithm actually a weighted summation of AS and informativeness is used.
       0.3 x informativeness + 0.7 x AS
MO

●   Objectives : each individual in
    the other subpopulation.
●   MO: number of individuals that
    dominate it.                      f2

                                           non-dominated

●   Non-dominated individuals              dominated



    have the highest fitness value.


                                                           f1
Performance Measures
●   Objective Fitness (OF)
    –   Evaluation against a fix set of test cases
    –   Here we use "all possible test cases" since we have
        picked problems with small sizes.

●   Objective Fitness Correlation (OFC)
    –   Correlation between OFs and fitness values in the
        coevolution (subjective fitness, SF).
Experimental Setup
●   Controlled experiments: GAAS
     –   GA with AS from exhaustive evaluation.




●   Compare the OF based on the same number of
    interactions.
Test Problems
●   Majority Function Problem (MFP)
    –   1D cellular automata problem
    –   Two parameters: radius (r) and problem size (n)

A sample IC with n = 9               0 1 0 1 0 0 1 1 1
                                      neighbor bits
                                          target bit

                            Input    000       001     010   011   100   101   110   111
A sample rule with r = 1
                            Output   0           0      0     1     0    1     1       1



                                          boolean-vector representation of this rule
Test Problems
●   Majority Function Problem (MFP)
Test Problems
●   Symbolic Regression Problem (SRP)
    –   Curve fitting with Genetic Programming trees
    –   Two measures: sum of error and hit
                      +            f(x)
                                          original function
GP Tree
                                          regression curve
                                                              hit
                 *         +


             -       x x       x


         x       x


                     2x
                                                                    x
Test Problems
●   Parity Problem (PP)
    –   Determine odd/even for the number of 1's in a bit
        string
    –   Two parameter: odd/even and bit string length (n)
         A problem with n = 10
                                 0 1 0 1 0 0 1 1 11

         A solution tree
Test Problems: PP
                                            5-even Parity
Boolean-vector       0 0 0 1 0                                  false (0)

                     D0 D1 D2 D3 D4


                                0
                               AND                      false
GP Tree

                      1               0
                     OR              AND


             1                   1          0
           NOT AND        D2    NOT OR     AND
                          0

          D0         D3        D0    D1    D1      D2
          0           1         0    0      0       0
Results of MFP (r=2, n=9)
Results of MFP (r=2, n=9)
Results of SRP   6   4
                 x −2x x
                            2
Results of SRP   6   4
                 x −2x x
                            2
Results of PP (odd, n=10)
Results of PP (odd, n=10)
Summary of Results
Multi-objective Approach

               ●   One run for COMO in
                   MFP.
               ●   OF drops when NDR
                   rises.
               ●   Why high NDR?
                   –   Duplicate solutions
                   –   Too many objectives
MO approach to improve WI
MFP
                        MO-WS-WI
MO approach to improve WI
SRP
                            MO-AS-WI
                            MO-WS-WI


                           WeiSum-AS-WI


                          MO-AS-AI
                          MO-WS-AI
MO approach to improve WI
PP




                   MO-AS-WI
Conclusions
●   MO2 approach with weighted informativeness
    (MO-AS-WI and MO-WS-WI) outperforms other
    evaluation methods in coevolution.
●   MO1 approach does not work well because
    there are usually too many objectives. This can
    be represented by a high NDR and results in a
    random search.
●   Coevolution is efficient for the MFP and SRP.
Issues
●   Test problems used are small, and there is not
    proof of generalizability to larger problems.


●   Implication to statistical learning: select not only
    difficult but also informative data for training.
Question?
Thank you!
Average Score
                  Solutions
           S1    S2 S3 S4 S5
      T1   0      1 0 0 1 2              0.4

      T2   0      0 1 1 0 2              0.4
Test  T3   0      1 1 0 0 2              0.4
cases T4   1      0 0 0 0 2              0.4
      T5   1      0 1 0 0 2              0.4

           2      2 3 1 1
           0.4   0.4   0.6   0.2   0.2




                                               Max(O(m),O(n))
Weighted Score
                Solutions
             S1 S2 S3 S4 S5
        T1   0 1 0 0 1        2
        T2   0 0 1 1 0        2
Test    T3   0 1 1 0 0        2
cases   T4   1 0 0 0 0        2
        T5   1 0 1 0 0        2
             2 2 3 1 1




                                      Max(O(m),O(n))
Average Informativeness




                Max(O(mn2),O(nm2))
Weighted Informativeness




                  Max(O(mn2),O(nm2))
MO




     Max(O(mn2),O(nm2))

Weitere ähnliche Inhalte

Andere mochten auch

Making the most out of corporate social responsibility
Making the most out of  corporate social responsibilityMaking the most out of  corporate social responsibility
Making the most out of corporate social responsibility
Aneesh Suresh
 
RESULT BASED M&E in FFA-revised
RESULT BASED M&E in FFA-revisedRESULT BASED M&E in FFA-revised
RESULT BASED M&E in FFA-revised
Stephen Musimba
 
Monitoring & evaluation presentation[1]
Monitoring & evaluation presentation[1]Monitoring & evaluation presentation[1]
Monitoring & evaluation presentation[1]
skzarif
 

Andere mochten auch (16)

Making the most out of corporate social responsibility
Making the most out of  corporate social responsibilityMaking the most out of  corporate social responsibility
Making the most out of corporate social responsibility
 
Comparison and evaluation of alternative designs
Comparison and evaluation of alternative designsComparison and evaluation of alternative designs
Comparison and evaluation of alternative designs
 
From theory based policy evaluation to smart policy design: lessons learned f...
From theory based policy evaluation to smart policy design: lessons learned f...From theory based policy evaluation to smart policy design: lessons learned f...
From theory based policy evaluation to smart policy design: lessons learned f...
 
RESULT BASED M&E in FFA-revised
RESULT BASED M&E in FFA-revisedRESULT BASED M&E in FFA-revised
RESULT BASED M&E in FFA-revised
 
CSR, Sustainable Business and Strategy
CSR, Sustainable Business and StrategyCSR, Sustainable Business and Strategy
CSR, Sustainable Business and Strategy
 
Step by step guide to sustainability planning
Step by step guide to sustainability planningStep by step guide to sustainability planning
Step by step guide to sustainability planning
 
Survey, comparison & evaluation of cross platform mobile application developm...
Survey, comparison & evaluation of cross platform mobile application developm...Survey, comparison & evaluation of cross platform mobile application developm...
Survey, comparison & evaluation of cross platform mobile application developm...
 
Outcome Mapping: Monitoring and Evaluation Tool
Outcome Mapping: Monitoring and Evaluation ToolOutcome Mapping: Monitoring and Evaluation Tool
Outcome Mapping: Monitoring and Evaluation Tool
 
Patagonia, integrating CSR into business model creation and strategic management
Patagonia, integrating CSR into business model creation and strategic managementPatagonia, integrating CSR into business model creation and strategic management
Patagonia, integrating CSR into business model creation and strategic management
 
Presentation Training on Result Based Management (RBM) for M&E Staff
Presentation Training on Result Based Management (RBM) for M&E StaffPresentation Training on Result Based Management (RBM) for M&E Staff
Presentation Training on Result Based Management (RBM) for M&E Staff
 
Results Based Monitoring and Evaluation
Results Based Monitoring and EvaluationResults Based Monitoring and Evaluation
Results Based Monitoring and Evaluation
 
Balanced Scorecard for Strategic Planning and Measurement
Balanced Scorecard for Strategic Planning and MeasurementBalanced Scorecard for Strategic Planning and Measurement
Balanced Scorecard for Strategic Planning and Measurement
 
Monitoring and Evaluation Framework
Monitoring and Evaluation FrameworkMonitoring and Evaluation Framework
Monitoring and Evaluation Framework
 
Monitoring & evaluation presentation[1]
Monitoring & evaluation presentation[1]Monitoring & evaluation presentation[1]
Monitoring & evaluation presentation[1]
 
Project Monitoring & Evaluation
Project Monitoring & EvaluationProject Monitoring & Evaluation
Project Monitoring & Evaluation
 
Results-Based Management in UNDP
Results-Based Management in UNDPResults-Based Management in UNDP
Results-Based Management in UNDP
 

Ähnlich wie A Comparison of Evaluation Methods in Coevolution 20070921 (10)

Selecting Discriminating Terms for Bug Assignment A Formal Analysis
Selecting Discriminating Terms for Bug Assignment A Formal AnalysisSelecting Discriminating Terms for Bug Assignment A Formal Analysis
Selecting Discriminating Terms for Bug Assignment A Formal Analysis
 
Promise 2011: "Selecting Discriminating Terms for Bug Assignment: A Formal An...
Promise 2011: "Selecting Discriminating Terms for Bug Assignment: A Formal An...Promise 2011: "Selecting Discriminating Terms for Bug Assignment: A Formal An...
Promise 2011: "Selecting Discriminating Terms for Bug Assignment: A Formal An...
 
การสุ่มตัวอย่างในงานวิจัยสาธารณสุข
การสุ่มตัวอย่างในงานวิจัยสาธารณสุขการสุ่มตัวอย่างในงานวิจัยสาธารณสุข
การสุ่มตัวอย่างในงานวิจัยสาธารณสุข
 
AlgoPerm2012 - 05 Ioan Todinca
AlgoPerm2012 - 05 Ioan TodincaAlgoPerm2012 - 05 Ioan Todinca
AlgoPerm2012 - 05 Ioan Todinca
 
T test statistics
T test statisticsT test statistics
T test statistics
 
Discrete Probability Distributions
Discrete  Probability DistributionsDiscrete  Probability Distributions
Discrete Probability Distributions
 
Algo complexity
Algo complexityAlgo complexity
Algo complexity
 
Clasification approaches
Clasification approachesClasification approaches
Clasification approaches
 
UML&FM 2012
UML&FM 2012UML&FM 2012
UML&FM 2012
 
Transactional Data Mining
Transactional Data MiningTransactional Data Mining
Transactional Data Mining
 

Mehr von Ting-Shuo Yo

Introduction to BCI
Introduction to BCIIntroduction to BCI
Introduction to BCI
Ting-Shuo Yo
 

Mehr von Ting-Shuo Yo (9)

20141030 ntustme computer_programmingandbeyond_share
20141030 ntustme computer_programmingandbeyond_share20141030 ntustme computer_programmingandbeyond_share
20141030 ntustme computer_programmingandbeyond_share
 
Tag2Card User's manual v01
Tag2Card User's manual v01Tag2Card User's manual v01
Tag2Card User's manual v01
 
InnoCentive
InnoCentiveInnoCentive
InnoCentive
 
Introduction to BCI
Introduction to BCIIntroduction to BCI
Introduction to BCI
 
Design Thinking and Innovation
Design Thinking and InnovationDesign Thinking and Innovation
Design Thinking and Innovation
 
Neighborhood Component Analysis 20071108
Neighborhood Component Analysis 20071108Neighborhood Component Analysis 20071108
Neighborhood Component Analysis 20071108
 
The Neurophysiology of Speech
The Neurophysiology of SpeechThe Neurophysiology of Speech
The Neurophysiology of Speech
 
Diffusion MRI, Tractography,and Connectivity: what machine learning can do?
Diffusion MRI, Tractography,and Connectivity: what machine learning can do?Diffusion MRI, Tractography,and Connectivity: what machine learning can do?
Diffusion MRI, Tractography,and Connectivity: what machine learning can do?
 
Simulating Weather: Numerical Weather Prediction as Computational Simulation
Simulating Weather: Numerical Weather Prediction as Computational SimulationSimulating Weather: Numerical Weather Prediction as Computational Simulation
Simulating Weather: Numerical Weather Prediction as Computational Simulation
 

Kürzlich hochgeladen

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 

Kürzlich hochgeladen (20)

Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu SubbuApidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 

A Comparison of Evaluation Methods in Coevolution 20070921

  • 1. Final Presentation INF/SCR-06-54 Applied Computing Science, ICS A Comparison of Evaluation Methods in Coevolution Ting-Shuo Yo Supervisor: Edwin D. de Jong Arno P.J.M. Siebes
  • 2. Outline ● Introduction ● Evaluation methods in coevolution ● Performance measures ● Test problems ● Results and discussion ● Concluding remarks
  • 3. Introduction ● Evolutionary computation ● Coevolution ● Coevolution for test-based problems ● Motivation of this study
  • 4. Genetic Algorithm Initialization 2. SELECTION Parents 1. EVALUATION 3. REPRODUCTION Population (crossover, mutation,...) 4. REPLACEMENT Offspring While (not TERMINATE) TERMINATE End
  • 5. Coevolution Initialization 1. EVALUATION ................ Subpopulation Subpopulation 2. SELECTION 2. SELECTION 3. REPRODUCTION 3. REPRODUCTION 4. REPLACEMENT 4. REPLACEMENT While (not TERMINATE) TERMINATE End
  • 6. Test-Based Problems f(x) original function regression curve s1 s2 s3 x t1 t2 t3 t4 t5 t6 t7 t8 t9 t10
  • 7. Coevolution for Test-Based Problems Test 1. EVALUATION population Interaction: 2. SELECTION ● Does the solution solve the 3. REPRODUCTION test? 4. REPLACEMENT ● How good does the solution perform on the test? Solution population Solutions: the more tests it solves the better. 2. SELECTION 3. REPRODUCTION Tests: the less solutions pass it 4. REPLACEMENT the better.
  • 8. Motivation ● Coevolution provides a way to select tests adaptively → stability and efficiency ● Solution concept → stability ● Efficiency depends on selection and evaluation. ● Compared to evaluation based on all relevant information, how do different coevolutionary evaluation methods perform?
  • 9. Concepts for Coevolutionary Evaluation Methods ● Interaction ● Distinction and informativeness ● Dominance and multi-objective approach
  • 10. Interaction ● A function that returns the outcome of interaction between two individuals from different subpopulations. – Checkers players: which one wins – Test / Solution: if the solution succeeds in solving the test S 1 S 2 S 3 S 4 S 5 sum T1 0 1 0 0 1 2 T2 0 0 1 1 0 2 ● Interaction matrix T3 0 1 1 0 0 2 T4 1 0 0 0 0 1 T5 1 0 1 0 0 2 sum 2 2 3 1 1
  • 11. Distinction Solutions T3 S1 S2 S3 S4 S5 sum S1 S2 S3 S4 S5 sum T1 0 1 0 0 1 2 S1 - 0 0 0 0 T2 0 0 1 1 0 2 S2 1 - 0 1 1 Test T3 0 1 1 0 0 2 S3 1 0 - 1 1 cases T4 1 0 0 0 0 1 S4 0 0 0 - 0 T5 1 0 1 0 0 2 S5 0 0 0 0 - sum 2 2 3 1 1 sum 2 0 0 2 2 6 ● Ability to keep diversity on the other subpopulation. ● Informativeness
  • 12. Dominance and MO approach f2 non-dominated S1 is dominated by S2 iff: dominated f1 ● Keep the best for each objective. ● MO: number of individuals that dominate it
  • 13. Evaluation Methods ● AS: Averaged Score ● WS: Weighted Score ● AI: Averaged Informativeness ● WI: Weighted Informativeness ● MO
  • 14. AS and WS ● AS : (# positive interaction) / (# all interaction) Solutions S1 S2 S3 S4 S5 sum T1 0 1 0 0 1 2 0.4 T2 0 0 1 1 0 2 0.4 Test T3 0 1 1 0 0 2 0.4 cases T4 1 0 0 0 0 1 0.2 T5 1 0 1 0 0 2 0.4 sum 2 2 3 1 1 0.4 0.4 0.6 0.2 0.2 ● WS : each interaction is weighted differently.
  • 15. AI and WI ● AI : # of distinctions it makes ● WI : each distinction is weighted differently. S1>S2 S1>S3 S1>S4 S1>S5 ............. T1 1 1 0 1 .... 5 T2 0 0 0 1 .... 2 T3 1 1 0 0 .... 6 T4 0 1 0 1 .... 2 T5 0 0 0 0 .... 1 In the algorithm actually a weighted summation of AS and informativeness is used. 0.3 x informativeness + 0.7 x AS
  • 16. MO ● Objectives : each individual in the other subpopulation. ● MO: number of individuals that dominate it. f2 non-dominated ● Non-dominated individuals dominated have the highest fitness value. f1
  • 17. Performance Measures ● Objective Fitness (OF) – Evaluation against a fix set of test cases – Here we use "all possible test cases" since we have picked problems with small sizes. ● Objective Fitness Correlation (OFC) – Correlation between OFs and fitness values in the coevolution (subjective fitness, SF).
  • 18. Experimental Setup ● Controlled experiments: GAAS – GA with AS from exhaustive evaluation. ● Compare the OF based on the same number of interactions.
  • 19. Test Problems ● Majority Function Problem (MFP) – 1D cellular automata problem – Two parameters: radius (r) and problem size (n) A sample IC with n = 9 0 1 0 1 0 0 1 1 1 neighbor bits target bit Input 000 001 010 011 100 101 110 111 A sample rule with r = 1 Output 0 0 0 1 0 1 1 1 boolean-vector representation of this rule
  • 20. Test Problems ● Majority Function Problem (MFP)
  • 21. Test Problems ● Symbolic Regression Problem (SRP) – Curve fitting with Genetic Programming trees – Two measures: sum of error and hit + f(x) original function GP Tree regression curve hit * + - x x x x x 2x x
  • 22. Test Problems ● Parity Problem (PP) – Determine odd/even for the number of 1's in a bit string – Two parameter: odd/even and bit string length (n) A problem with n = 10 0 1 0 1 0 0 1 1 11 A solution tree
  • 23. Test Problems: PP 5-even Parity Boolean-vector 0 0 0 1 0 false (0) D0 D1 D2 D3 D4 0 AND false GP Tree 1 0 OR AND 1 1 0 NOT AND D2 NOT OR AND 0 D0 D3 D0 D1 D1 D2 0 1 0 0 0 0
  • 24. Results of MFP (r=2, n=9)
  • 25. Results of MFP (r=2, n=9)
  • 26. Results of SRP 6 4 x −2x x 2
  • 27. Results of SRP 6 4 x −2x x 2
  • 28. Results of PP (odd, n=10)
  • 29. Results of PP (odd, n=10)
  • 31. Multi-objective Approach ● One run for COMO in MFP. ● OF drops when NDR rises. ● Why high NDR? – Duplicate solutions – Too many objectives
  • 32. MO approach to improve WI MFP MO-WS-WI
  • 33. MO approach to improve WI SRP MO-AS-WI MO-WS-WI WeiSum-AS-WI MO-AS-AI MO-WS-AI
  • 34. MO approach to improve WI PP MO-AS-WI
  • 35. Conclusions ● MO2 approach with weighted informativeness (MO-AS-WI and MO-WS-WI) outperforms other evaluation methods in coevolution. ● MO1 approach does not work well because there are usually too many objectives. This can be represented by a high NDR and results in a random search. ● Coevolution is efficient for the MFP and SRP.
  • 36. Issues ● Test problems used are small, and there is not proof of generalizability to larger problems. ● Implication to statistical learning: select not only difficult but also informative data for training.
  • 39. Average Score Solutions S1 S2 S3 S4 S5 T1 0 1 0 0 1 2 0.4 T2 0 0 1 1 0 2 0.4 Test T3 0 1 1 0 0 2 0.4 cases T4 1 0 0 0 0 2 0.4 T5 1 0 1 0 0 2 0.4 2 2 3 1 1 0.4 0.4 0.6 0.2 0.2 Max(O(m),O(n))
  • 40. Weighted Score Solutions S1 S2 S3 S4 S5 T1 0 1 0 0 1 2 T2 0 0 1 1 0 2 Test T3 0 1 1 0 0 2 cases T4 1 0 0 0 0 2 T5 1 0 1 0 0 2 2 2 3 1 1 Max(O(m),O(n))
  • 41. Average Informativeness Max(O(mn2),O(nm2))
  • 42. Weighted Informativeness Max(O(mn2),O(nm2))
  • 43. MO Max(O(mn2),O(nm2))