LEADER 11551nam 22008535 450 001 9910484703203321 005 20230329132800.0 010 $a3-662-44303-1 024 7 $a10.1007/978-3-662-44303-3 035 $a(CKB)3710000000227443 035 $a(SSID)ssj0001338715 035 $a(PQKBManifestationID)11857512 035 $a(PQKBTitleCode)TC0001338715 035 $a(PQKBWorkID)11344619 035 $a(PQKB)11218972 035 $a(DE-He213)978-3-662-44303-3 035 $a(MiAaPQ)EBC6287497 035 $a(MiAaPQ)EBC5584925 035 $a(Au-PeEL)EBL5584925 035 $a(OCoLC)889715722 035 $a(PPN)180625896 035 $a(EXLCZ)993710000000227443 100 $a20140821d2014 u| 0 101 0 $aeng 135 $aurnn#008mamaa 181 $ctxt 182 $cc 183 $acr 200 10$aGenetic Programming $e17th European Conference, EuroGP 2014, Granada, Spain, April 23-25, 2014, Revised Selected Papers /$fedited by Miguel Nicolau, Krzysztof Krawiec, Malcolm I. Heywood, Mauro Castelli, Pablo García-Sánchez, Juan J. Merelo, Victor Manuel Rivas Santos, Kevin Sim 205 $a1st ed. 2014. 210 1$aBerlin, Heidelberg :$cSpringer Berlin Heidelberg :$cImprint: Springer,$d2014. 215 $a1 online resource (XII, 247 p. 78 illus.) 225 1 $aTheoretical Computer Science and General Issues,$x2512-2029 ;$v8599 300 $aBibliographic Level Mode of Issuance: Monograph 311 $a3-662-44302-3 327 $aIntro -- Preface -- Organization -- Table of Contents -- Oral Presentations -- Higher Order Functions for Kernel Regression -- 1 Introduction -- 2 Kernel Regression -- 3 Higher Order Functions -- 4 Method -- 4.1 Wrapper Approach to the Evolution of Distance Measures -- 4.2 Experiment Design -- 5 Results Analysis -- 6 Conclusion and Future Work -- References -- Flash: A GP-GPU Ensemble Learning System for Handling Large Datasets -- 1 Introduction -- 2 Related Work: Accelerating GP with GPUs -- 3 The Core GP Learner -- 3.1 Mean Squared Error and Pearson Correlation on GPUs -- 3.2 Individual Level Parallelism -- 4 Flash - The GP-GPU Ensemble Learning System -- 4.1 GP Instances -- 4.2 Generating a Fused Model -- 5 Experimental Setup -- 5.1 Million Song Dataset Year Prediction Challenge -- 5.2 Ensemble Configurations -- 6 Results -- 6.1 Prediction Error Analysis -- 6.2 Prediction Error vs. GP Instances -- 6.3 Runtime Analysis -- 7 Conclusions and Future Work -- References -- Learning Dynamical Systems Using Standard Symbolic Regression -- 1 Introduction -- 2 Background -- 2.1 Genetic Programming and Symbolic Regression -- 2.2 Differential Equations and First-Order Approximation -- 3 Proposed Approach -- 4 Case Study -- 5 Experimental Results -- 5.1 Noise-Free Data -- 5.2 Absolute Noise -- 5.3 Noise 5% -- 5.4 Noise 10% -- 6 Results Discussion -- 7 Conclusions and Future Works -- References -- Semantic Crossover Based on the Partial Derivative Error -- 1 Introduction -- 2 Semantic Crossover Based on Partial Derivative Error -- 2.1 Backpropagation -- 2.2 Selecting the Crossing Points -- 3 Results -- 4 Conclusions -- References -- A Multi-dimensional Genetic Programming Approach for Multi-class Classification Problems -- 1 Introduction -- 2 Related Work -- 3 Formulation of Multi-dimensional GP -- 4 Algorithm -- 5 Experimental Analysis -- 5.1 Data Sets. 327 $a5.2 Experiments with GP Classifiers -- 5.3 Comparison with Various Classifiers -- 6 Conclusions and Future Directions -- References -- Generalisation Enhancement via Input Space Transformation: A GP Approach -- 1 Introduction -- 2 Related Works -- 3 Proposed Approach -- 3.1 Trees Return Multiple Outputs -- 3.2 FitnessMeasure -- 4 Experiments and Analysis -- 4.1 Experimental Settings -- 4.2 Results -- 5 Conclusions -- References -- On Diversity, Teaming, and Hierarchical Policies: Observations from the Keepaway Soccer Task -- 1 Introduction -- 2 Related Work -- 3 Hierarchical Symbiotic Policy Search -- 3.1 Symbiont -- 3.2 Variation Operators -- 3.3 Selection Operator -- 3.4 Constructing Hierarchical Policies -- 3.5 Fitness and Diversity -- 4 Results -- 5 Conclusion -- References -- Genetically Improved CUDA C++ Software -- 1 Introduction -- 2 Source Code: StereoCamera -- 3 Example Stereo Pairs from Microsoft's I2I Database -- 4 Pre- and Post- Evolution Tuning and Post Evolution Minimisation of Code Changes -- 5 Alternative Implementations -- 5.1 Avoiding Reusing Threads: XHALO -- 5.2 Parallel of Discrepancy Offsets: DPER -- 6 Parameters Accessible to Evolution -- 6.1 Fixed Configuration Parameters -- 7 Evolvable Code -- 7.1 Initial Population -- 7.2 Weights -- 7.3 Mutation -- 7.4 Crossover -- 7.5 Fitness -- 7.6 Selection -- 8 Results -- 8.1 GP Better Than Random Search -- 9 Evolved Tesla K20c CUDA Code -- 10 Conclusions -- References -- Measuring Mutation Operators' Exploration-Exploitation Behaviour and Long-Term Biases -- 1 Introduction -- 1.1 Reader's Guide -- 2 Related Work -- 3 Statistics on Markov Chains -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Measuring Exploration-Exploitation Behaviour -- 4.3 Exploration-Exploitation Behaviour and Search Space Coverage -- 4.4 Exploration-Exploitation Behaviour and Performance. 327 $a4.5 Stationary Distributions -- 5 Conclusions -- 5.1 Limitations -- 5.2 Future Work -- References -- Exploring the Search Space of Hardware / Software Embedded Systems by Means of GP -- 1 Introduction -- 2 Previous Work -- 2.1 Hardware -- 2.2 Software -- 3 Proposed Extensions -- 3.1 Evolvable Hardware Topology Related Changes -- 3.2 Input Modules -- 3.3 Problem Encoding and Search Method -- 4 Experimental Results -- 4.1 Newton-Raphson Division -- 4.2 Finding the Maximum -- 4.3 Parity -- 5 Conclusions -- References -- Enhancing Branch-and-Bound Algorithms for Order Acceptance and Scheduling with Genetic Programming -- 1 Introduction -- 1.1 Goals -- 1.2 Organisation -- 2 Methodology -- 2.1 Branch and Bound Algorithm for OAS -- 3 Computational Results -- 3.1 Datasets -- 3.2 Results -- 4 Conclusions -- References -- Using Genetic Improvement and Code Transplants to Specialise a C++ Program to a Problem Class -- 1 Introduction -- 2 Genetic Improvement with Multi-donor Transplantation and Specialisation -- 3 Experimental Setup -- 4 Results -- 4.1 Transplanting from MiniSAT-best09 -- 4.2 Transplanting from MiniSAT-bestCIT -- 4.3 Transplanting from MiniSAT-best09 and MiniSAT-bestCIT -- 4.4 Combining Results -- 5 Summary of Related Work -- 6 Conclusions -- References -- ESAGP - A Semantic GP Framework Based on Alignment in the Error Space -- 1 Introduction -- 2 Alignment in the Error Space -- 3 One Step Error Space Alignment GP: ESAGP-1 -- 4 Two Steps Error Space Alignment GP: ESAGP-2 -- 5 Experimental Study -- 6 Conclusions and Future Work -- References -- Building a Stage 1 Computer Aided Detector for Breast Cancer Using Genetic Programming -- 1 Introduction -- 2 Mammography -- 2.1 Computer-Aided Detection of Mammographic Abnormalities -- 2.2 Feature Extraction -- 2.3 Related Work -- 3 Workflow -- 3.1 Separation -- 3.2 Suppression of the Background. 327 $a3.3 Segmentation -- 3.4 Textural Features -- 4 Experimental Setup -- 4.1 GP Setup -- 5 Results -- 6 Conclusions and Future Work -- References -- NEAT, There's No Bloat -- 1 Introduction -- 2 Bloat -- 2.1 Causes of Bloat and Bloat Control Methods -- 2.2 The Secret Behind Operator Equalization -- 3 NeuroEvolution of Augmenting Topologies -- 3.1 NEAT Features -- 3.2 NEAT, GP and Bloat -- 4 Experiments -- 4.1 Discussion -- 5 Concluding Remarks and Future Work -- References -- Posters -- The Best Things Don't Always Come in Small Packages: Constant Creation in Grammatical Evolution -- 1 Introduction -- 2 Background -- 3 Experiments -- 3.1 Problem Suite and Evolutionary Parameters -- 3.2 Results -- 3.3 Discussion -- 4 Conclusions -- References -- Asynchronous Evolution by Reference-Based Evaluation: Tertiary Parent Selection and Its Archive -- 1 Introduction -- 2 Tierra-Based Asynchronous Genetic Programming -- 2.1 Overview -- 2.2 Algorithm -- 3 Asynchronous Reference-Based Evaluation -- 3.1 Concept -- 3.2 Algorithm -- 4 Experiment -- 4.1 Settings -- 4.2 Results -- 5 Conclusion -- References -- Behavioral Search Drivers for Genetic Programing -- 1 Introduction -- 2 Background -- 3 Motivation -- 4 Behavioral Evaluation of Programs in GP -- 5 TheExperiment -- 6 Related Work -- 7 Conclusion -- References -- Cartesian Genetic Programming: Why No Bloat? -- 1 Introduction -- 2 Cartesian Genetic Programming -- 3 Bloat and CGP -- 3.1 Neutral Genetic Drift -- 3.2 Length Bias -- 4 Experiments -- 4.1 Regular CGP -- 4.2 No Neutral Genetic Drift -- 4.3 Recurrent CGP -- 4.4 Neutral Search -- 5 Results -- 5.1 Regular CGP -- 5.2 No Neutral Genetic Drift -- 5.3 Recurrent CGP -- 5.4 Neutral Search -- 6 Discussion -- 7 Conclusion -- References -- On Evolution of Multi-category Pattern Classifiers Suitable for Embedded Systems -- 1 Introduction. 327 $a2 Cartesian Genetic Programming -- 2.1 Representation -- 2.2 Search Algorithm -- 3 Evolutionary Design of Classifiers -- 4 Experimental Setup -- 5 Experimental Results -- 5.1 Evaluation of the Evolved Classifiers -- 6 Conclusion -- References -- Author Index. 330 $aThe book constitutes the refereed proceedings of the 17th European Conference on Genetic Programming, Euro GP 2014, held in Grenada, Spain, in April 2014 co-located with the Evo*2014 events, Evo BIO, Evo COP, Evo MUSART and Evo Applications. The 15 revised full papers presented together with 5 poster papers were carefully reviewed and selected form 40 submissions. The wide range of topics in this volume reflects the current state of research in the field. Thus, we see topics as diverse as search-based software engineering, image analysis, dynamical systems, evolutionary robotics and operational research to the foundations of search as characterized through semantic variation operators. 410 0$aTheoretical Computer Science and General Issues,$x2512-2029 ;$v8599 606 $aAlgorithms 606 $aComputer science 606 $aArtificial intelligence 606 $aApplication software 606 $aAlgorithms 606 $aTheory of Computation 606 $aArtificial Intelligence 606 $aComputer and Information Systems Applications 615 0$aAlgorithms. 615 0$aComputer science. 615 0$aArtificial intelligence. 615 0$aApplication software. 615 14$aAlgorithms. 615 24$aTheory of Computation. 615 24$aArtificial Intelligence. 615 24$aComputer and Information Systems Applications. 676 $a006.31 702 $aNicolau$b Miguel$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aKrawiec$b Krzysztof$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aHeywood$b Malcolm I$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aCastelli$b Mauro$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aGarcía-Sánchez$b Pablo$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aMerelo$b Juan J$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aRivas Santos$b Victor Manuel$4edt$4http://id.loc.gov/vocabulary/relators/edt 702 $aSim$b Kevin$4edt$4http://id.loc.gov/vocabulary/relators/edt 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910484703203321 996 $aGenetic Programming$9772374 997 $aUNINA