A compiler for CPPNs: transforming phenotypic descriptions into genotypic representations

Aus de_evolutionary_art_org
Version vom 28. November 2015, 16:31 Uhr von Gubachelier (Diskussion | Beiträge)

(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Wechseln zu: Navigation, Suche


Reference

Risi, Sebastian: A compiler for CPPNs: transforming phenotypic descriptions into genotypic representations. In: Proceedings of the AAAI Fall Symposium Series (2013)

DOI

Abstract

Biologically-inspired AI methods like evolutionary algorithms have shown great promise in creating complex structures yet these structures still pale in comparison to their natural counterparts. The recently introduced generative encoding compositional pattern producing networks (CPPNs), which is based on the principles of how natural organisms develop, narrowed this gap by showing that it is possible to artificially evolve life-like patterns with regularities at a high-level of abstraction. As these generative and developmental systems (GDS) are asked to evolve increasingly complex structures, the question of how to start evolution from a promising part of the search space becomes more and more important. To address this challenge, we introduce the concept of a CPPN-Compiler, which allows the user to directly compile a high-level description of the desired starting structure into the CPPN itself. In this paper, as proof of concept, the CPPN-Compiler is able to generate CPPN-encoded representations from vector-based images that can serve as the starting point for further evolution. Importantly, the offspring of these compiled CPPNs show meaningful variations because they directly embody important domain-specific regularities like symmetry or repetition. Thus the results presented in this paper open up a new research direction in GDS, in which specialized CPPN-Compilers for different domains could help to overcome the black box of evolutionary optimization.

Extended Abstract

Bibtex

Used References

Auerbach, J. E., and Bongard, J. C. 2011. Evolving complete robots with cppn-neat: the utility of recurrent connections. In Proceedings of the 13th annual conference on Genetic and evolutionary computation, 1475–1482. ACM.

Cheney, N.; MacCurdy, R.; Clune, J.; and Lipson, H. 2013. Unshackling evolution: Evolving soft robots with multiple materials and a powerful generative encoding. In Proceed- ings of the Genetic and Evolutionary Computation Confer- ence.

Clune, J., and Lipson, H. 2011. Evolving 3d objects with a generative encoding inspired by developmental biology. In Proceedings of the European Conference on Artificial Life (Alife-2011), volume 5, 2–12. New York, NY, USA: ACM.

Clune, J.; Beckmann, B. E.; Ofria, C.; and Pennock, R. T. 2009. Evolving coordinated quadruped gaits with the Hy- perNEAT generative encoding. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC-2009) Spe- cial Section on Evolutionary Robotics. NJ, USA: IEEE Press.

Clune, J.; Chen, A.; and Lipson, H. 2013. Upload any object and evolve it: Injecting complex geometric patterns into cppns for further evolution. In Proceedings of the IEEE Congress on Evolutionary Computation.

Cybenko, G. 1989. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems 2(4):303–314.

D’Ambrosio, D. B.; Lehman, J.; Risi, S.; and Stanley, K. O. 2010. Evolving policy geometry for scalable multiagent learning. In Proceedings of the 9th International Confer- ence on Autonomous Agents and Multiagent Systems: vol- ume 1-Volume 1, 731–738. International Foundation for Au- tonomous Agents and Multiagent Systems.

Gauci, J., and Stanley, K. O. 2008. A case study on the critical role of geometric regularity in machine learning. In Proceedings of the Twenty-Third AAAI Conference on Ar- tificial Intelligence (AAAI-2008). Menlo Park, CA: AAAI Press.

Gauci, J., and Stanley, K. O. 2010. Autonomous evolution of topographic regularities in artificial neural networks. Neural Comput. 22:1860–1898.

Hoover, A. K.; Szerlip, P. A.; Norton, M. E.; Brindle, T. A.; Merritt, Z.; and Stanley, K. O. 2012. Generating a com- plete multipart musical composition from a single mono- phonic melody with functional scaffolding. In Proceedings of the International Conference on Computational Creativ- ity (ICCC-2012). Dublin, Ireland.

Hoover, A. K.; Szerlip, P. A.; and Stanley, K. O. 2011. Inter- actively evolving harmonies through functional scaffolding. In Proceedings of the Genectic and Evolutionary Computa- tion Conference (GECCO-2011). New York, NY: The Asso- ciation for Computing Machinery.

Lehman, J., and Stanley, K. O. 2010. Revising the evo- lutionary computation abstraction: Minimal criteria novelty search. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2010). ACM.

Lehman, J., and Stanley, K. O. 2011. Abandoning objec- tives: Evolution through the search for novelty alone. Evo- lutionary Computation 19(2):189–223.

Reich, D. E.; Cargill, M.; Bolk, S.; Ireland, J.; Sabeti, P. C.; Richter, D. J.; Lavery, T.; Kouyoumjian, R.; Farhadian, S. F.; Ward, R.; et al. 2001. Linkage disequilibrium in the human genome. Nature 411(6834):199–204.

Risi, S., and Stanley, K. O. 2012. An enhanced hypercube- based encoding for evolving the placement, density, and connectivity of neurons. Artificial Life 18(4):331–363.

Risi, S.; Lehman, J.; D’Ambrosio, D. B.; Hall, R.; and Stan- ley, K. O. 2012. Combining search-based procedural con- tent generation and social gaming in the petalz video game. In Proceedings of the Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE 2012).

Risi, S.; Cellucci, D.; and Lipson, H. 2013. Ribosomal robots: Evolved designs inspired by protein folding. In Pro- ceedings of the Genetic and Evolutionary Computation Con- ference.

Secretan, J.; Beato, N.; D’Ambrosio, D.; Rodriguez, A.; Campbell, A.; Folsom-Kovarik, J.; and Stanley, K. 2011. Picbreeder: A case study in collaborative evolutionary ex- ploration of design space. Evolutionary Computation 19(3):373–403.

Stanley, K. O., and Miikkulainen, R. 2002. Evolving neu- ral networks through augmenting topologies. Evolutionary Computation 10:99–127.

Stanley, K. O., and Miikkulainen, R. 2004. Competitive coevolution through evolutionary complexification. JAIR 21:63–100.

Stanley, K. O.; D’Ambrosio, D. B.; and Gauci, J. 2009. A hypercube-based indirect encoding for evolving large-scale neural networks. Artificial Life 15(2):185–212.

Stanley, K. O. 2007. Compositional pattern producing net- works: A novel abstraction of development. Genetic Pro- gramming and Evolvable Machines Special Issue on Devel- opmental Systems 8(2):131–162.

Verbancsics, P., and Stanley, K. O. 2011. Constraining Con- nectivity to Encourage Modularity in HyperNEAT. In Pro- ceedings of the Genetic and Evolutionary Computation Con- ference (GECCO 2011). New York, NY: ACM.

Woolley, B. G., and Stanley, K. O. 2011. On the deleterious effects of a priori objectives on evolution and representation. In Proceedings of the 13th annual conference on Genetic and evolutionary computation, 957–964. ACM.


Links

Full Text

https://pure.itu.dk/portal/files/62966261/risi_aaai2013.pdf

https://www.aaai.org/ocs/index.php/FSS/FSS13/paper/view/7597/7516

intern file

Sonstige Links

https://www.aaai.org/ocs/index.php/FSS/FSS13/paper/view/7597