Generative Representations for Evolutionary Design Automation: Unterschied zwischen den Versionen
(Die Seite wurde neu angelegt: „ == Reference == Hornby, G.S.: Generative Representations for Evolutionary Design Automation. PhD thesis, Boston, MA (2003). == DOI == == Abstract == In thi…“) |
(kein Unterschied)
|
Aktuelle Version vom 18. November 2014, 15:05 Uhr
Inhaltsverzeichnis
Reference
Hornby, G.S.: Generative Representations for Evolutionary Design Automation. PhD thesis, Boston, MA (2003).
DOI
Abstract
In this thesis the class of generative representations is de�ned and it is shown that this class of representations improves the scalability of evolutionary design systems by automat- ically learning inductive bias of the design problem thereby capturing design dependencies and better enabling search of large design spaces. First, properties of representations are identi�ed as: combination, control-�ow, and abstraction. Using these properties, representa- tions are classi�ed as non-generative, or generative. Whereas non-generative representations use elements of encoded artifacts at most once in translation from encoding to actual ar- tifact, generative representations have the ability to reuse parts of the data structure for encoding artifacts through control-�ow (using iteration) and/or abstraction (using labeled procedures). Unlike non-generative representations, which do not scale with design com- plexity because they cannot capture design dependencies in their structure, it is argued that evolution with generative representations can better scale with design complexity because of their ability to hierarchically create assemblies of modules for reuse, thereby enabling better search of large design spaces. Second, GENRE, an evolutionary design system us- ing a generative representation, is described. Using this system, a non-generative and a generative representation are compared on four classes of designs: three-dimensional static structures constructed from voxels; neural networks; actuated robots controlled by oscilla- tor networks; and neural network controlled robots. Results from evolving designs in these substrates show that the evolutionary design system is capable of �nding solutions of higher �tness with the generative representation than with the non-generative representation. This improved performance is shown to be a result of the generative representation's ability to ixcapture intrinsic properties of the search space and its ability to reuse parts of the encod- ing in constructing designs. By capturing design dependencies in its structure, variation operators are more likely to be successful with a generative representation than with a non- generative representation. Second, reuse of data elements in encoded designs improves the ability of an evolutionary algorithm to search large design spaces.
Extended Abstract
Bibtex
Used References
[1] H. Abelson and A. A. diSessa. Turtle Geometry. M.I.T. Press, 1982.
[2] H. Abelson, G. J. Sussman, and J. Sussman. Structure and Interpretation of Computer Programs. McGraw-Hill, second edition, 1996.
[3] M. Agarwal and J. Cagan. The language of co�ee makers. Environment and Planning B: Planning and Design, 25(2):205�226, 1998.
[4] M. Agarwal, J. Cagan, and G. Stiny. A micro language: Generating mems resonators using a coupled form-function shape grammar. Environment and Planning B: Planning and Design, 27:615�626, 2000.
[5] J. T. Alander. An indexed bibliography of genetic algorithms with fuzzy logic. In W. Pedrycz, editor, Fuzzy Evolutionary Computation, pages 299-�318. Kluwer Aca- demic, Boston, 1997.
[6] B. Alberts, A. Johnson, J. Lewis, M. Ra�, K. Roberts, and P. Walter. Molecular Biology of The Cell. Garland Publishing, New York, 4th edition, 2002.
[7] L. Altenberg. The evolution of evolvability in genetic programming. In K. Kinnear, editor, Advances in Genetic Programming, pages 47�74. MIT Press, 1994.
[8] P. Angeline and J. B. Pollack. Coevolving high-level representations. In C. Lang- ton, editor, Proceedings of the Third Workshop on Arti�cial Life, Reading, MA, 1994. Addison-Wesley.
[9] P. J. Angeline. Morphogenic evolutionary computations: Introduction, issues and examples. In J. McDonnell, B. Reynolds, and D. Fogel, editors, Proc. of the Fourth Annual Conf. on Evolutionary Programming, pages 387�401. MIT Press, 1995.
[10] P. J. Angeline, G. M. Saunders, and J. B. Pollack. An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks, 5(1):54� 65, 1994.
[11] T. Bäck, F. Ho�meister, and H.-P. Schwefel. A survey of evolution strategies. In R. K. Belew and L. B. Booker, editors, Proc. of the Fourth Intl. Conf. on Genetic Algorithms, pages 2�9. Morgan Kaufmann, 1991.
[12] Thomas Bäck. Evolutionary Algorithms in Theory and Practice. Oxford University Press, New York, 1996.
213[13] P. Baron, A. Tuson, and R. Fisher. A voxel based representation for evolutionary shape optimisation. Journal of Arti�cial Intelligence for Engineering Design, Analysis and Manufacturing, Special Issue on Evolutionary Design, 13(3), 1999.
[14] A. Barr. Superquadrics and angle preserving transformations. IEEE Computer Graph- ics and Applications, 1(1):11�23, 1981.
[15] P. Bentley and S. Kumar. Three ways to grow designs: A comparison of embryogenies of an evolutionary design problem. In Banzhaf, Daida, Eiben, Garzon, Honavar, Jakiel, and Smith, editors, Genetic and Evolutionary Computation Conference, pages 35�43, 1999.
[16] P. J. Bentley. Generic Evolutionary Design of Solid Objects Using a Genetic Algorithm. PhD thesis, University of Hudders�eld, 1996.
[17] P. J. Bentley and J. P. Wake�eld. The evolution of solid object designs using genetic algorithms. In V. Rayward-Smith, editor, Modern Heuristic Search Methods, pages 199�215. John Wiley and Sons Inc., 1996.
[18] E. J. W. Boers and H. Kuiper. Biological metaphors and the design of modular arti�cial neural networks. Master's thesis, Leidea University, the Netherlands, 1992.
[19] E. J. W. Boers, H. Kuiper, B. L. M. Happel, and I.G. Sprinkhuizen-Kuyper. Designing modular arti�cial neural networks. In H.A. Wijsho�, editor, Proceedings of Computing Science in The Netherlands, pages 87�96, SION, Stichting Mathematisch Centrum, 1993.
[20] E. Bonabeau, S. Guérin, D. Snyers, P. Kuntz, and G. Theraulaz. Three-dimensional architectures grown by simple `stigmergic' agents. BioSystems, 56(1):13�32, 2000.
[21] J. C. Bongard and R. Pfeifer. Repeated structure and dissociation of genotypic and phenotypic complexity in arti�cial ontogeny. In Genetic and Evolutionary Computation Conference, pages 829�836, 2001.
[22] T. Broughton, A. Tan, and P. S. Coates. The use of genetic programming in exploring 3d design worlds. In R. Junge, editor, CAAD Futures 1997. Kluwer Academic, 1997.
[23] I. Chen and J. Burdick. Determining task optimal robot assembly con�gurations. In IEEE International Conference on Robotics and Automation., pages 132�137, 1995.
[24] O. Chocron and P. Bidaud. Genetic design of 3D modular manipulators. In IEEE International Conference on Robotics and Automation, pages 223�-228, 1997.
[25] P. Coates, T. Broughton, and H. Jackson. Exploring three-dimensional design worlds using lindenmayer systems and genetic programming. In P. J. Bentley, editor, Evolu- tionary Design by Computers, 1999.
[26] D. Dasgupta and D. McGregor. Sga: A structured genetic algorithm. Technical Report IKBS-8-92, University of Strathclyde, 1992.
214[27] D. Dasgupta and D. R. McGregor. Designing neural networks using the structured genetic algorithm. In I. Aleksander and J. Taylor, editors, Arti�cial Neural Networks, 2, pages 263�268, New York, 1992. Elsevier.
[28] R. Dawkins. The Blind Watchmaker. Harlow Longman, 1986.
[29] R. Dawkins. The evolution of evolvability. In C.G. Langton, editor, Arti�cial Life, pages 201�220. Addison Wesley, 1989.
[30] H. de Garis. Arti�cial embryology : The genetic programming of an arti�cial em- bryo. In Branko Soucek and the IRIS Group, editors, Dynamic, Genetic and Chaotic Programming. Wiley, 1992.
[31] P. Dittrich, J. Ziegler, and W. Banzhaf. Arti�cial chemistries - a review. Arti�cial Life, 7(3):225�275, 2001.
[32] K. E. Drexler. Biological and nanomechanical systems. In C.G. Langton, editor, Arti�cial Life, pages 501�519. Addison Wesley, 1989.
[33] P. Eggenberger. Cell interaction for development in evolutionary robotics. In P. Maes, M. Mataric, J.-A. Meyer, J. Pollack, and S. W. Wilson, editors, From Animals to Animats 4, pages 440�448, Cambridge, MA, 1996. MIT Press Bradford Books.
[34] P. Eggenberger. Evolving morphologies of simulated 3d organisms based on di�erential gene expression. In P. Husbands and I. Harvey, editors, Proc. of the 4rth European Conf. on Arti�cial Life, pages 440�448, Cambridge, 1997. MIT Press.
[35] A. E. Eiben, R. Nabuurs, and I. Booij. The escher evolver: Evolution to the people. In P. J. Bentley and D. W. Corne, editors, Creative Evolutionary Systems, chapter 17, pages 425�439. Morgan Kaufmann, San Francisco, 2001.
[36] S. Farritor and S. Dubowsky. On modular design of �eld robotic systems. Autonomous Robots, 10(1):57�65, 2001.
[37] S. Farritor, S. Dubowsky, N Rutman, and J. Cole. A systems level modular design approach to �eld robotics. In IEEE International Conference on Robotics and Au- tomation, pages 2890�2895, 1996.
[38] G. B. Fogel and D. B. Fogel. Continuous evolutionary programming: Analysis and experiments. Journal of Cybernetics and Systems, 26:79�90, 1995.
[39] L. J. Fogel, A. J. Owens, and M. J. Walsh. Arti�cial Intelligence Through Simulated Evolution. Wiley Publishing, New York, 1966.
[40] C. M. Fonseca and P. J. Fleming. An overview of evolutionary algorithms in multiob- jective optimization. Evolutionary Computation, 3(1):1�16, 1995.
[41] J. Frazer. Reptiles. Architectural Design, pages 231�239, April 1974. [42] J. Frazer. An Evolutionary Architecture. Architectural Association Publications, 1995.
[43] J. Frazer. Creative design and the generative evolutionary paradigm. In P. J. Bentley and D. W. Corne, editors, Creative Evolutionary Systems, chapter 9, pages 253�274. Morgan Kaufmann, San Francisco, 2001.
[44] J. Frazer and J. Connor. A conceptual seeding technique for architectural design. In Proc. of the International Conference on the Application of Computers in Architectural Design, pages 425�34, Berlin, 1979. Online Conferences with AMK.
[45] K. Fredriksson. Genetic algorithms and generative encoding of neural networks for some benchmark classi�cation problems. In Proceedings of the Third Nordic Work- shop on Genetic Algorithms and their Applications (3NWGA), pages 123�134. Finnish Arti�cial Intelligence Society (FAIS), 1997.
[46] C. M. Friedrich and C. Moraga. An evolutionary method to �nd good building-blocks for architectures of arti�cial neural networks. In Proc. of the Sixth Intl. Conf. on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU '96), pages 951�956, Granada, Spain, 1996.
[47] P. Funes. Evolution of Complexity in Real-World Domains. PhD thesis, Dept. of Computer Science, Brandeis University, May 2001.
[48] P. Funes and J. Pollack. Computer evolution of buildable objects. In Phil Husbands and Inman Harvey, editors, Proceedings of the Fourth European Conference on Arti�- cial Life, pages 358�367, Cambridge, MA, 1997. MIT Press.
[49] P. Funes and J. B. Pollack. Evolutionary body building: Adaptive physical designs for robots. Arti�cial Life, 4(4):337�357, 1998.
[50] F. Gruau. Genetic synthesis of modular neural networks. In Proceedings of the Fifth International Conference on Genetic Algorithms, pages 318�325. Morgan-Kaufman, 1993.
[51] F. Gruau. Neural Network Synthesis Using Cellular Encoding and the Genetic Algo- rithm. PhD thesis, Ecole Normale Supérieure de Lyon, 1994.
[52] F. Gruau. Automatic de�nition of modular neural networks. Adaptive Behaviour, 3(2):151�183, 1995.
[53] R. Grzeszczuk and D. Terzopoulos. Automated learning of muscle-actuated locomo- tion through control abstraction. In SIGGRAPH 95 Conference Proceedings, Annual Conference Series, pages 63�70, Los Angeles, California, August 1995. In Computer Graphics Annual Conf. Series, 1995.
[54] M. Hemberg, U.-M. O'Reilly, and P. Nordin. GENR8: A design tool for surface generation. In Late Breaking paper at the Genetic and Evolutionary Computation Conference, 2001.
[55] J. H. Holland. Adaptation in Natural and Arti�cial Systems. University of Michigan Press, Ann Arbor, 1975.
216[56] G. S. Hornby, M. Fujita, S. Takamura, T. Yamamoto, and O. Hanagata. Autonomous evolution of gaits with the sony quadruped robot. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 1297�1304. Morgan Kaufmann, 1999.
[57] G. S. Hornby, H. Lipson, and J. B. Pollack. Generative representations for the au- tomatic design of modular physical robots. IEEE Transactions on Robotics and Au- tomation, in press.
[58] G. S. Hornby, H. Lipson, and J. B. Pollack. Evolution of generative design systems for modular physical robots. In IEEE Intl. Conf. on Robotics and Automation, pages 4146�4151, 2001.
[59] G. S. Hornby and J. B. Pollack. The advantages of generative grammatical encodings for physical design. In Congress on Evolutionary Computation, pages 600�607, 2001.
[60] G. S. Hornby and J. B. Pollack. Body-brain coevolution using L-systems as a generative encoding. In Genetic and Evolutionary Computation Conference, pages 868�875, 2001.
[61] G. S. Hornby and J. B. Pollack. Evolving L-systems to generate virtual creatures. Computers and Graphics, 25(6):1041�1048, 2001.
[62] G. S. Hornby and J. B. Pollack. Creating high-level components with a generative representation for body-brain evolution. Arti�cial Life, 8(3), 2002.
[63] G. S. Hornby, S. Takamura, O. Hanagata, M. Fujita, and J. Pollack. Evolution of controllers from a high-level simulator to a high dof robot. In J. Miller, editor, Evolvable Systems: from biology to hardware; Proc. of the Third Intl. Conf. (ICES 2000), Lecture Notes in Computer Science; Vol. 1801, pages 80�89. Springer, 2000.
[64] C. C. Huang and A. Kusiak. Modularity in design of products and systems. IEEE Transactions on Systems, Man, and Cybernetics, Part A, 28(1):66�77, 1998.
[65] P. Husbands, G. Germy, M. McIlhagga, and R. Ives. Two applications of genetic algorithms to component design. In T. Fogarty, editor, Evolutionary Computing. LNCS 1143, pages 50�61. Springer-Verlag, 1996.
[66] H. Jackson. Toward a symbiotic coevolutionary approach to architecture. In P. J. Bentley and D. W. Corne, editors, Creative Evolutionary Systems, chapter 11, pages 299�313. Morgan Kaufmann, San Francisco, 2001.
[67] C. Jacob. Genetic L-system Programming. In Y. Davidor and P. Schwefel, editors,
Parallel Problem Solving from Nature III, Lecture Notes in Computer Science, volume
866, pages 334�343, 1994.
[68] C. Jacob. Evolution programs evolved. In H.-M. Voigt, W. Ebeling, I. Rechenberg, and H.-P. Schwefel, editors, Parallel Problem Solving from Nature PPSN-IV, Lecture Notes in Computer Science 1141, pages 42�51, Berlin, 1996. Springer-Verlag.
[69] C. Jacob. Evolving evolution programs. In J. R. Koza, K. Deb, M. Dorigo, D. B. Fogel, M. Garzon, H. Iba, and R. Riolo, editors, Proceedings of the First Annual Conference on Genetic Programming, pages 107�115. Morgan Kaufmann, 1996.
217[70] N. Jakobi. Minimal Simulations for Evolutionary Robotics. PhD thesis, School of Cognitive and Computing Sciences, University of Sussex, May 1998.
[71] T. Jones. Evolutionary Algorithms, Fitness Landscapes and Search. PhD thesis, Uni- versity of New Mexico, 1995.
[72] C. Kane and M. Schoenauer. Genetic operators for two-dimentional shape optimiza- tion. In J.-M. Alliot, E. Lutton, E. Ronald, M. Schoenauer, and D. Snyers, editors, Arti�ciale Evolution - EA95. Springer-Verlag, 1995.
[73] C. Kane and M. Schoenauer. Topological optimum design. Control and Cybernetics, 25(5):1059�1088, 1996.
[74] J.-O. Kim and P. K. Khosla. Design of space shuttle tile servicing robot: An application of task based kinematic design. In IEEE International Conference on Robotics and Automation., pages 867�874, 1993.
[75] S. Kirkpatrick, C.D. Gelatt, and M.P. Vecchi. Optimization by simulated annealing. Science, 220:671�680, 1983.
[76] H. Kitano. Designing neural networks using genetic algorithms with graph generation system. Complex Systems, 4:461�476, 1990.
[77] J. Kodjabachian and J. A. Meyer. Evolution and development of modular control architectures for 1-d locomotion in six-legged animats. Connection Science, 10:211� 237, 1998.
[78] M. Komosinski. The world of framsticks: Simulation, evolution, interaction. In Virtual Worlds 2, Lecture Notes in Arti�cial Intelligence 1834, pages 214�224. Springer-Verlag, 2000.
[79] M. Komosinski and A. Rotaru-Varga. Comparison of di�erent genotype encodings for simulated 3d agents. Arti�cial Life, 7(4):395�418, 2001.
[80] M. Komosinski and S. Ulatowski. Framsticks: Towards a simulation of a nature-like world, creatures and evolution. In J.-D. Nicoud D. Floreano and F. Mondada, editors, Proceedings of 5th European Conference on Arti�cial Life (ECAL99), volume 1674 of Lecture Notes in Arti�cial Intelligence, pages 261�265. Springer-Verlag, 1999.
[81] J. R. Koza. Genetic Programming: on the programming of computers by means of natural selection. MIT Press, Cambridge, Mass., 1992.
[82] J. R. Koza. Genetic Programming II : Automatic Discovery of Reusable Programs. MIT Press, Cambridge, Mass., 1994.
[83] P. C. Leger. Automated Synthesis and Optimization of Robot Con�gurations: An Evo- lutionary Approach. PhD thesis, The Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, 1999.
[84] B. Lewin. Genes VII. Oxford University Press, 2000.
[85] D. S. Linden. Innovative antenna design using genetic algorithms. In P. J. Bentley and D. W. Corne, editors, Creative Evolutionary Systems, chapter 20, pages 487�510. Morgan Kaufmann, San Francisco, 2001.
[86] A. Lindenmayer. Mathematical models for cellular interaction in development. parts I and II. Journal of Theoretical Biology, 18:280�299 and 300�315, 1968.
[87] A. Lindenmayer. Adding continuous components to L-Systems. In G. Rozenberg and A. Salomaa, editors, L Systems, Lecture Notes in Computer Science 15, pages 53�68. Springer-Verlag, 1974.
[88] H. Lipson and J. B. Pollack. Automatic design and manufacture of robotic lifeforms. Nature, 406:974�978, 2000.
[89] S. Luke and L. Spector. Evolving graphs and networks with edge encoding: Prelim- inary report. In J. Koza, editor, Late-breaking Papers of Genetic Programming 96, pages 117�124. Stanford Bookstore, 1996.
[90] C. Mautner and R. Belew. Coupling morphology and control in an evolved robot. In Banzhaf, Daida, Eiben, Garzon, Honavar, Jakiel, and Smith, editors, Genetic and Evolutionary Computation Conference, pages 1350�1357, 1999.
[91] C. Mautner and R. Belew. Evolving robot morphology and control. In M. Sugisaka, editor, Proc. of Articial Life and Robotics(AROB99), Oita, 1999.
[92] B. Meyer. Object-oriented Software Construction. Prentice Hall, New York, 1988.
[93] Z. Michalewicz, D. Dasgupta, R. G. Le Riche, and M. Schoenauer. Evolutionary algo- rithms for constrained engineering problems. Computers and Industrial Engineering Journal, 30(2):851�870, 1996.
[94] Zbigniew Michalewicz. Genetic Algorithms + Data Structures = Evolution Programs. Springer-Verlag, New York, 1992.
[95] G. F. Miller, P. M. Todd, and S. U. Hegde. Designing neural netowrks using ge- netic algorithms. In J. D. Scha�er, editor, Proc. of the Third Intl. Conf. on Genetic Algorithms, pages 379�384, San Mateo, California, 1989. Morgan Kaufman.
[96] D. Montana and L. Davis. Training feedforward networks using genetic algorithms. In Intl. Joint Conf. on Articial Intelligence, pages 762�767, San Mateo, California, 1989. Morgan Kaufman.
[97] J. T. Ngo and J. Marks. Spacetime constraints revisited. In SIGGRAPH 93 Conference Proceedings, pages 343�350, 1993. Annual Conference Series.
[98] H. Nishino, H. Takagi, S.-B. Cho, and K. Utsumiya. A 3D modeling system for creative design. In 15th Intl. Conf. on Information Networking, pages 479�486, Beppu, Japan, 2001.
[99] S. Nol� and D. Parisi. Growing neural networks. Technical Report PCIA-91-15, 1991. 219[100] S. Nol� and D. Parisi. Evolving arti�cial neural networks that develop in time. In F. Morán, A. Moreno, J. J. Merelo, and P. Chacón, editors, European Conference on Arti�cial Life, pages 353�367. Springer, 1995.
[101] G. Ochoa. On genetic algorithms and lindenmayer systems. In A. Eiben, T. Baeck, M. Schoenauer, and H. P. Schwefel, editors, Parallel Problem Solving from Nature V, pages 335�344. Springer-Verlag, 1998.
[102] C. Paredis, H. Brown, and P. Khosla. A rapidly deployable manipulator system. In IEEE International Conference on Robotics and Automation., pages 1434�1439, 1996.
[103] J. B. Pollack, H. Lipson, G. Hornby, and P. Funes. Three generations of automatically designed robots. Arti�cial Life, 7(3):215�223, 2001.
[104] P. Prusinkiewicz and A. Lindenmayer. The Algorithmic Beauty of Plants. Springer- Verlag, 1990.
[105] G. Robinson, M. El-Beltagy, and A. Keane. Optimization in mechanical design. In P. J. Bentley, editor, Evolutionary Design by Computers, chapter 6, pages 147�165. Morgan Kaufmann, San Francisco, 1999.
[106] S. Rooke. Eons of genetically evolved algorithmic images. In P. J. Bentley and D. W. Corne, editors, Creative Evolutionary Systems, chapter 13, pages 339�365. Morgan Kaufmann, San Francisco, 2001.
[107] M. Rosenman. A growth model for form generation using a hierarchical evolutionary approach. Microcomputer in Civil Engineering, 11:161�172, 1996.
[108] M. Rosenman and J. Gero. Evolving designs by generating useful complex gene struc- tures. In P. J. Bentley, editor, Evolutionary Design by Computers, chapter 15, pages 345�364. Morgan Kaufmann, San Francisco, 1999.
[109] M. A. Rosenman. The generation of form using an evolutionary approach. In D. Das- gupta and Z. Michalewicz, editors, Evolutionary Algorithms in Engineering Applica- tions, pages 69�85, Southampton, 2001. Springer-Verlag.
[110] G. P. Roston. A Genetic Methodology for Con�guration Design. PhD thesis, Dept. of Mechanical Engineering, Carnegie Mellon University, December 1994.
[111] A. Rowbottom. Evolutionary art and form. In P. J. Bentley, editor, Evolutionary Design by Computers, chapter 11, pages 262�277. Morgan Kaufmann, San Francisco, 1999.
[112] D. Sanko� and J. B. Kruskal, editors. Time warps, string edits and macromolecules: the theory and practice of sequence comparison. Addison-Wesley, Reading, Mass., 1983.
[113] M. Schoenauer. Representations for evolutionary optimization and identi�cation in structural mechanics. In J. Periaux and G. Winter, editors, Genetic Algorithms in Engineering and Computer Science, chapter 22. John Wiley and Sons Ltd., 1995.
[114] M. Schoenauer. Shape representations and evolution schemes. In L. J. Fogel, P. J. Angeline, and T. Bäck, editors, Evolutionary Programming 5. MIT Press, 1996.
[115] K. Shea, J. Cagan, and S. J. Fenves. A shape annealing approach to optimal truss design with dynamic grouping of members. Journal of Mechanical Design, 119:388� 394, September 1997.
[116] K. Sims. Arti�cial Evolution for Computer Graphics. Computer Graphics, 25(4):319� 328, 1991.
[117] K. Sims. Evolving 3d morphology and behavior by competition. In R. Brooks and P. Maes, editors, Proceedings of the Fourth Workshop on Arti�cial Life, pages 28�39, Boston, MA, 1994. MIT Press.
[118] K. Sims. Evolving Virtual Creatures. In SIGGRAPH 94 Conference Proceedings, Annual Conference Series, pages 15�22, 1994.
[119] C. Soddu and E. Colabella. The morphogenetic design as an arti�cial intelligence system to support the management of design procedures through the total quality of the built-environment. In Proc. of The Management of Information Technology for Construction. First International Conference, Singapore, August 17-20, 1993.
[120] G. Stiny. Introduction to shape and shape grammars. Environment and Planning B: Planning and Design, 7:343�351, 1980.
[121] W. A. Tackett. Greedy recombination and genetic search on the space of computer pro- grams. In L. D. Whitley and M. D. Vose, editors, Foundations of Genetic Algorithms 3, pages 271�298. Morgan Kaufmann, 1995.
[122] T. Taura and I. Nagasaka. Adative-growth-type 3d geometric representation for spa- tial design. Journal of Arti�cial Intelligence for Engineering Design, Analysis and Manufacturing, 13(3):171�184, 1999.
[123] T. Taura, I. Nagasaka, and A. Yamagishi. An application of evolutionary programming to shape design. Computer-Aided Design, 30(1):29�35, 1998.
[124] T. Taylor and C. Massey. Recent developments in the evolution of morphologies and controllers for physically simulated creatures. Arti�cial Life, 7(1):77�87, 2001.
[125] P. Testa, U.-M. O'Reilly, M. Kangas, and A. Kilian. Moss: Morphogenetic surface structure - a software tool for design exploration. In Proceedings of Greenwich 2000: Digital Creativity Symposium, 2000.
[126] S. Todd and W. Latham. Evolutionary Art and Computers. Academic Press, 1992.
[127] S. Todd and W. Latham. The mutation and growth of art by computers. In P. J. Bentley, editor, Evolutionary Design by Computers, chapter 9, pages 221�250. Morgan Kaufmann, San Francisco, 1999.
221[128] S. J. P. Todd and W. Latham. Mutator, a subjective human interface for evolution of computer scultpures. Technical report, IBM United Kingdom Scienti�c Centre Report 248, 1991.
[129] K. Ulrich and K. Tung. Fundamentals of product modularity. Issues in De- sign/Manufacture Integration - 1991 American Society of Mechanical Engineers, De- sign Engineering Division (Publication) DE, 39:73�79, 1991.
[130] M. van de Panne and E. Fiume. Sensor-actuator Networks. In SIGGRAPH 93 Con- ference Proceedings, Annual Conference Series, pages 335�342, 1993.
[131] J. Ventrella. Explorations in the emergence of morphology and locomotion behavior in animated characters. In R. Brooks and P. Maes, editors, Proceedings of the Fourth Workshop on Arti�cial Life, Boston, MA, 1994. MIT Press.
[132] J. Ventrella. Sexual swimmers: Emergent morphology and locomotion without a �tness function. In P. Maes, M. Mataric, J.-A. Meyer, J. Pollack, and S. W. Wilson, editors, From Animals to Animats 4, pages 484�493, Cambridge, MA, 1996. MIT Press Bradford Books.
[133] J. Ventrella. Animated arti�cial life. In J.-C. Heudin, editor, Virtual Worlds: Synthetic Universes, Digital Life, and Complexity. Perseus Books, 1999.
[134] G. P. Wagner and L. Altenberg. Complex adaptations and the evolution of evolvability. Evolution, 50:967�976, 1996.
[135] M. Whitelaw. Breeding aesthetic objects: Art and arti�cial evolution. In P. J. Bentley and D. W. Corne, editors, Creative Evolutionary Systems, chapter 3, pages 129�145. Morgan Kaufmann, San Francisco, 2001.
[136] D. Whitley, T. Starkweather, and C. Bogart. Genetic algorithms and neural networks: optimizing connections and connectivity. Parallel Computing, 14:347�361, 1990.
[137] X. Yao. Evolving arti�cial neural networks. Proceedings of the IEEE, 87(9):1423�1447, 1999.
Links
Full Text
http://idesign.ucsc.edu/papers/hornby_phd.pdf
Sonstige Links
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.8827
