Free cookie consent management tool by TermsFeed Policy Generator

Changes between Version 14 and Version 15 of UsersSamples


Ignore:
Timestamp:
02/17/11 11:03:12 (14 years ago)
Author:
gkronber
Comment:

restructuring

Legend:

Unmodified
Added
Removed
Modified

  • UsersSamples

    v14 v15  
    33This section provides additional sample files for the HeuristicLab 3.3 Optimizer some of which are included as demo samples in the Optimizer.
    44
    5  * [#ESGriewank Evolution Strategy - Griewank]: An evolution strategy which solves the 10-dimensional Griewank test function
     5== Travelling Salesman ==
    66 * [#GATSP Genetic Algorithm - TSP]: A genetic algorithm which solves rge "ch130" travelling salesman problem (imported from TSPLIB)
    7  * [#GPAA Genetic programming for artificial ant problem]: A standard genetic programming algorithm for the artificial ant problem (Santa-Fe ant trail)
    8  * [#GPSR Genetic programming for symbolic regression]: A standard genetic programming algorithm to solve a symbolic regression problem (Boston Housing dataset)
    97 * [#IslandGA Island Genetic Algorithm - TSP]: An island genetic algorithm which solves the "ch130" traveling salesman problem (imported from TSPLIB)
    10  * [#LSKnapsack Local Search - Knapsack]: A local search algorithm that solves a randomly generated Knapsack problem
    11  * [#SARastrigin Simulated Annealing - Rastrigin]: A simulated annealing algorithm that solves the 2-dimensional Rastrigin test function
    128 * [#TSTSP Tabu Search - TSP]: A tabu search algorithm that solves the "ch130" TSP (imported from TSPLIB)
    139
    1410----
    1511
    16 [=#ESGriewank]
    17 == Evolution Strategy - Griewank ==
    18 A pre-defined evolution strategy which solves the 10-dimensional [TestFunctions#GriewankFunction Griewank test function]. HeuristicLab 3 provides a set of real valued test functions for benchmarking purposes. For a full overview please go the [TestFunctions Test Functions] wiki page.
    19 
    20 '''Algorithm:''' [[Evolution Strategy]]
    21 
    22 '''Algorithm Parameters:'''
    23  * Population Size: 20
    24  * Children: 500
    25  * !MaximumGenerations: 200
    26  * !ParentsPerChild: 5
    27  * !PlusSelection: False (Comma Selection)
    28  * Recombinator: !AverageCrossover
    29  * Mutator: !NormalAllPositionsManipulator
    30 
    31 '''Problem:''' [[Single Objective Test Function]]
    32 
    33 '''Problem Parameters:'''
    34  * !BestKnownQuality: 0
    35  * !BestKnownSolution: [0;0;0;0;0;0;0;0;0;0]
    36  * Bounds: [-600, 600]
    37  * Evaluator: !GriewankEvaluator
    38  * Maximization: False
    39  * !ProblemSize: 10
    40  * !SolutionCreator: !UniformRandomRealVectorCreator
    41 
    42 ----
    43 
    4412[=#GATSP]
    45 == Genetic Algorithm - TSP ==
     13=== Genetic Algorithm - TSP ===
    4614This sample demonstrates how to employ a genetic algorithm to optimize a travelling salesman problem instance, namely "ch130" from the [http://comopt.ifi.uni-heidelberg.de/software/TSPLIB95/ TSP Lib].
    4715
    … …  
    7139----
    7240
    73 [=#GPAA]
    74 == Genetic programming for artificial ant problem ==
    75 [[Image(SantaFe Result.png, width=500, right, margin-right=30, margin-left=30)]]
    76 
    77 '''Algorithm:''' [[Genetic Algorithm]]
    78 
    79 '''Algorithm Parameters:'''
    80  * Analyzer: !MultiAnalyzer
    81  * Crossover: !SubtreeCrossover - An operator which performs subtree swapping crossover
    82  * Elites: 1
    83  * !MaximumGenerations: 100
    84  * !MutationProbability: 15%
    85  * Mutator: !MultiSymbolicExpressionTreeManipulator
    86  * Population Size: 500
    87  * Seed: -
    88  * Selector: !TournamentSelector
    89  * !SetSeedRandomly: True
    90 
    91 '''Problem:''' [[Artificial Ant Problem]]
    92 
    93 '''Problem Parameters:'''
    94  * !ArtificialAntExpressionGrammar: !IfFoodAhead, Prog2, Prog3, Right, Left, Move
    95  * !BestKnownQuality: 89
    96  * Evaluator: !ArtificialAntEvaluator
    97  * !MaxExpressionDepth: 6
    98  * !MaxExpressionLength: 50
    99  * !MaxFunctionArguments: 3
    100  * !MaxFunctionDefinitions: 3
    101  * Maximization: True
    102  * !MaxTimeSteps: 600
    103  * !SolutionCreator: !ProbabilisticTreeCreator
    104  * World: 32x32 grid, 89 randomly scattered food items
    105 
    106 ----
    107 
    108 [=#GPSR]
    109 == Genetic programming for symbolic regression ==
    110 
    111 '''Algorithm:''' [[Genetic Algorithm]]
    112 
    113 '''Algorithm Parameters:'''
    114 
    115 '''Problem:''' [[Symbolic Regression Problem]]
    116 
    117 '''Problem Parameters:'''
    118  * !BestKnownQuality: null
    119  * !DataAnalysisProblemData: Data imported from Housing Dataset from UCI Repository (cf. http://archive.ics.uci.edu/ml/datasets/Housing)
    120  * Evaluator: !SymbolicRegressionScaledMeanSquaredErrorEvaluator
    121  * !FunctionTreeGrammar: Addition, Subtraction, Multiplication, Division, Constant, Variable
    122  * !LowerEstimationLimit: -289,08968253968254
    123  * !MaxExpressionDepth: 10
    124  * !MaxExpressionLength: 100
    125  * !MaxFunctionArguments: 0
    126  * !MaxFunctionDefiningBranches: 0
    127  * Maximization: False
    128  * !SolutionCreator: !ProbabilisticTreeCreator
    129  * !SymbolicExpressionTreeInterpreter: -
    130  * !UpperEstimationLimit: 332,91031746031746
    131 
    132 ----
    133 
    13441[=#IslandGA]
    135 == Island Genentic Algorithm - TSP ==
     42=== Island Genentic Algorithm - TSP ===
    13643
    13744'''Algorithm:''' [[IslandGA| Island Genetic Algorithm]]
    … …  
    17077----
    17178
     79[=#TSTSP]
     80=== Tabu Search - TSP ===
     81
     82'''Algorithm:''' [[TS| Tabu Search]]
     83
     84'''Algorithm Parameters:'''
     85 * Analyzer: !MultiAnalyzer
     86 * !MaximumIterations: 1000
     87 * !MoveEvaluator: TSPInversionMoveRoundedEuclideanPathEvaluator
     88 * !MoveGenerator: !StochasticInversionMultiMoveGenerator
     89 * !MoveMaker: !InversionMoveMaker
     90 * !SampleSize: 500
     91 * Seed: -
     92 * !SetSeedRandomly: True
     93 * !TabuChecker: !InversionMoveSoftTabuCriterion
     94 * !TabuMaker: !InversionMoveTabuMaker
     95 * !TabuTenure: 60
     96
     97'''Problem:''' [[Travelling Salesman Problem]]
     98
     99'''Problem Parameters:'''
     100 * !BestKnownQuality: 6110
     101 * !BestKnownSolution: The best known solution of this TSP instance (cf. TSP Lib)
     102 * Coordinates: The x and y coordinates of the cities
     103 * !DistanceMatrix: null
     104 * Evaluator: TSPRoundedEuclideanPathEvaluator
     105 * Maximization: False
     106 * !SolutionCreator: !RandomPermutationCreator
     107 * !UseDistanceMatrix: True
     108
     109
     110
     111== Real-valued Test Functions ==
     112 * [#ESGriewank Evolution Strategy - Griewank]: An evolution strategy which solves the 10-dimensional Griewank test function
     113 * [#SARastrigin Simulated Annealing - Rastrigin]: A simulated annealing algorithm that solves the 2-dimensional Rastrigin test function
     114----
     115
     116[=#ESGriewank]
     117=== Evolution Strategy - Griewank ===
     118A pre-defined evolution strategy which solves the 10-dimensional [TestFunctions#GriewankFunction Griewank test function]. HeuristicLab 3 provides a set of real valued test functions for benchmarking purposes. For a full overview please go the [TestFunctions Test Functions] wiki page.
     119
     120'''Algorithm:''' [[Evolution Strategy]]
     121
     122'''Algorithm Parameters:'''
     123 * Population Size: 20
     124 * Children: 500
     125 * !MaximumGenerations: 200
     126 * !ParentsPerChild: 5
     127 * !PlusSelection: False (Comma Selection)
     128 * Recombinator: !AverageCrossover
     129 * Mutator: !NormalAllPositionsManipulator
     130
     131'''Problem:''' [[Single Objective Test Function]]
     132
     133'''Problem Parameters:'''
     134 * !BestKnownQuality: 0
     135 * !BestKnownSolution: [0;0;0;0;0;0;0;0;0;0]
     136 * Bounds: [-600, 600]
     137 * Evaluator: !GriewankEvaluator
     138 * Maximization: False
     139 * !ProblemSize: 10
     140 * !SolutionCreator: !UniformRandomRealVectorCreator
     141
     142----
     143
     144[=#SARastrigin]
     145=== Simulated Annealing - Rastrigin ===
     146
     147'''Algorithm:''' [[SA| Simulated Annealing]]
     148
     149'''Algorithm Parameters:'''
     150 * Analyzer: !MultiAnalyzer
     151 * !AnnealingOperator: !ExponentialDiscreteDoubleValueModifier
     152 * !EndTemperature: 1E-06
     153 * !InnerIterations: 50
     154 * !MaximumIterations: 1000
     155 * !MoveEvaluator: !RastriginAdditiveMoveEvaluator
     156 * !MoveGenerator: !StochasticNormalMultiMoveGenerator
     157 * !MoveMaker: !AdditiveMoveMaker
     158 * Seed: -
     159 * !SetSeedRandomly: True
     160 * !StartTemperature: 1
     161
     162'''Problem:''' [[Single Objective Test Function]]
     163
     164'''Problem Parameters:'''
     165 * !BestKnownQuality: 0
     166 * !BestKnownSolution: [0;0]
     167 * Bounds: ([-5, 12], [-5,12])
     168 * Evaluator: !RastriginEvaluator
     169 * Maximization: False
     170 * !ProblemSize: 2
     171 * !SolutionCreator: !UniformRandomRealVectorCreator
     172
     173
     174== Genetic Programming ==
     175 * [#GPArtificialAnt Genetic programming for artificial ant problem]: A standard genetic programming algorithm to solve an artificial ant problem (Santa-Fe ant trail)
     176 * [#GPSymbolicRegressionBostonHousing Genetic programming for symbolic regression (Boston Housing)]: A standard genetic programming algorithm to solve a symbolic regression problem (Boston Housing dataset)
     177 * [#GPSymbolicRegressionTower Genetic programming for symbolic regression (Tower)]: A genetic programming algorithm to solve a symbolic regression problem (Tower dataset)
     178 * [#GPSymbolicRegressionMackeyGlass Genetic programming for symbolic regression (Mackey-Glass)]: A genetic programming algorithm to create a one-step prediction model for a chaotic time series (Mackey-Glass time series)
     179 * [#GPSymbolicClassificationWisconsin Genetic programming for symbolic classification (Wisconsin)]: A genetic programming algorithm to solve a symbolic classification problem (Wisconsin Diagnostic Breast Cancer dataset)
     180 * [#GPSymbolicClassificationMammography Genetic programming for symbolic classification (Mammography)]: A genetic programming algorithm to solve a symbolic classification problem (Mammography dataset)
     181
     182----
     183
     184[=#GPAA]
     185=== Genetic programming for artificial ant problem ===
     186[[Image(SantaFe Result.png, width=500, right, margin-right=30, margin-left=30)]]
     187
     188'''Algorithm:''' [[Genetic Algorithm]]
     189
     190'''Algorithm Parameters:'''
     191 * Analyzer: !MultiAnalyzer
     192 * Crossover: !SubtreeCrossover - An operator which performs subtree swapping crossover
     193 * Elites: 1
     194 * !MaximumGenerations: 100
     195 * !MutationProbability: 15%
     196 * Mutator: !MultiSymbolicExpressionTreeManipulator
     197 * Population Size: 500
     198 * Seed: -
     199 * Selector: !TournamentSelector
     200 * !SetSeedRandomly: True
     201
     202'''Problem:''' [[Artificial Ant Problem]]
     203
     204'''Problem Parameters:'''
     205 * !ArtificialAntExpressionGrammar: !IfFoodAhead, Prog2, Prog3, Right, Left, Move
     206 * !BestKnownQuality: 89
     207 * Evaluator: !ArtificialAntEvaluator
     208 * !MaxExpressionDepth: 6
     209 * !MaxExpressionLength: 50
     210 * !MaxFunctionArguments: 3
     211 * !MaxFunctionDefinitions: 3
     212 * Maximization: True
     213 * !MaxTimeSteps: 600
     214 * !SolutionCreator: !ProbabilisticTreeCreator
     215 * World: 32x32 grid, 89 randomly scattered food items
     216
     217----
     218
     219[=#GPSR]
     220=== Genetic programming for symbolic regression ===
     221
     222'''Algorithm:''' [[Genetic Algorithm]]
     223
     224'''Algorithm Parameters:'''
     225
     226'''Problem:''' [[Symbolic Regression Problem]]
     227
     228'''Problem Parameters:'''
     229 * !BestKnownQuality: null
     230 * !DataAnalysisProblemData: Data imported from Housing Dataset from UCI Repository (cf. http://archive.ics.uci.edu/ml/datasets/Housing)
     231 * Evaluator: !SymbolicRegressionScaledMeanSquaredErrorEvaluator
     232 * !FunctionTreeGrammar: Addition, Subtraction, Multiplication, Division, Constant, Variable
     233 * !LowerEstimationLimit: -289,08968253968254
     234 * !MaxExpressionDepth: 10
     235 * !MaxExpressionLength: 100
     236 * !MaxFunctionArguments: 0
     237 * !MaxFunctionDefiningBranches: 0
     238 * Maximization: False
     239 * !SolutionCreator: !ProbabilisticTreeCreator
     240 * !SymbolicExpressionTreeInterpreter: -
     241 * !UpperEstimationLimit: 332,91031746031746
     242
     243
     244== Additional ==
     245
     246 * [#LSKnapsack Local Search - Knapsack]: A local search algorithm that solves a randomly generated Knapsack problem
     247
     248----
     249
    172250[=#LSKnapsack]
    173 == Local Search - Knapsack ==
     251=== Local Search - Knapsack ===
    174252
    175253'''Algorithm:''' [[LocalSearch| Local Search]]
    … …  
    198276 * Weights: The weights of the items.
    199277
    200 ----
    201 
    202 [=#SARastrigin]
    203 == Simulated Annealing - Rastrigin ==
    204 
    205 '''Algorithm:''' [[SA| Simulated Annealing]]
    206 
    207 '''Algorithm Parameters:'''
    208  * Analyzer: !MultiAnalyzer
    209  * !AnnealingOperator: !ExponentialDiscreteDoubleValueModifier
    210  * !EndTemperature: 1E-06
    211  * !InnerIterations: 50
    212  * !MaximumIterations: 1000
    213  * !MoveEvaluator: !RastriginAdditiveMoveEvaluator
    214  * !MoveGenerator: !StochasticNormalMultiMoveGenerator
    215  * !MoveMaker: !AdditiveMoveMaker
    216  * Seed: -
    217  * !SetSeedRandomly: True
    218  * !StartTemperature: 1
    219 
    220 '''Problem:''' [[Single Objective Test Function]]
    221 
    222 '''Problem Parameters:'''
    223  * !BestKnownQuality: 0
    224  * !BestKnownSolution: [0;0]
    225  * Bounds: ([-5, 12], [-5,12])
    226  * Evaluator: !RastriginEvaluator
    227  * Maximization: False
    228  * !ProblemSize: 2
    229  * !SolutionCreator: !UniformRandomRealVectorCreator
    230 
    231 ----
    232 
    233 [=#TSTSP]
    234 == Tabu Search - TSP ==
    235 
    236 '''Algorithm:''' [[TS| Tabu Search]]
    237 
    238 '''Algorithm Parameters:'''
    239  * Analyzer: !MultiAnalyzer
    240  * !MaximumIterations: 1000
    241  * !MoveEvaluator: TSPInversionMoveRoundedEuclideanPathEvaluator
    242  * !MoveGenerator: !StochasticInversionMultiMoveGenerator
    243  * !MoveMaker: !InversionMoveMaker
    244  * !SampleSize: 500
    245  * Seed: -
    246  * !SetSeedRandomly: True
    247  * !TabuChecker: !InversionMoveSoftTabuCriterion
    248  * !TabuMaker: !InversionMoveTabuMaker
    249  * !TabuTenure: 60
    250 
    251 '''Problem:''' [[Travelling Salesman Problem]]
    252 
    253 '''Problem Parameters:'''
    254  * !BestKnownQuality: 6110
    255  * !BestKnownSolution: The best known solution of this TSP instance (cf. TSP Lib)
    256  * Coordinates: The x and y coordinates of the cities
    257  * !DistanceMatrix: null
    258  * Evaluator: TSPRoundedEuclideanPathEvaluator
    259  * Maximization: False
    260  * !SolutionCreator: !RandomPermutationCreator
    261  * !UseDistanceMatrix: True