CAP6938 Neuroevolution and Developmental Encoding Developmental EncodingGoal: Evolve Systems of Biological ComplexityDevelopmentSolving this Problem Could Solve Many OthersSolution Has Two PartsEmbryogeny is Powerful Because of ReuseThe Unfolding of Structure Allows ReuseRediscovery Unnecessary with ReuseTherefore, Developmental EncodingSome Major Issues in AEDevelopmental EncodingsGrammatical Example 1L-System Evolution SuccessesGrowth of a TableGrammatical Example 2Cell Chemistry EncodingsCell Chemistry Example: Bongard’s Artificial OntogenyCell Chemistry Example 2Differences in AE ImplementationsCell FateTargetingHeterochronyCanalizationComplexification through Gene DuplicationGeneral Alignment ProblemHistorical Markings (NEAT) Solve the Alignment ProblemExploring the Space of AEHow Can We Learn How Developmental Encoding Works?The Holy GrailNext ClassesCAP6938Neuroevolution and Developmental EncodingDevelopmental Encoding Dr. Kenneth StanleyOctober 2, 2006Goal: Evolve Systems of Biological Complexity•Complexification only goes so far•100 trillion connections in the human brain•30,000 genes in the human genome•How is this possible?Development(embryo image from nobelprize.org)Solving this Problem Could Solve Many OthersSolution Has Two Parts•Complexification: Get into high-dimensional genotype space•Development: Get into high-dimensional phenotype space–Artificial embryogeny–Artificial ontogeny–Computational embryogeny–Computational embryology–Developmental Encoding–Indirect Encoding–Generative Mapping–…Embryogeny is Powerful Because of Reuse•Genetic information is reused during embryo development•Many structures share information•Allows enormous complexity to be encoded compactly(James Madison University http://orgs.jmu.edu/strength/KIN_425/kin_425_muscles_calves.htm)The Unfolding of Structure Allows ReuseRediscovery Unnecessary with Reuse•Repeated substructures should only need to be represented once•Then repeated elaborations do not require rediscovery•Rediscovery is expensive and improbable•(Development is powerful for search even though it is a property of the mapping)Therefore, Developmental Encoding•Indirect encoding: Genes do not map directly to units of structure in phenotype•Phenotype develops from embryo into mature form•Genetic material can be reused•Many existing developmental encoding systemsSome Major Issues in AE•Phenotypic duplication can be brittle•Variation on an established convention is powerful•Reuse with variation is common in natureDevelopmental Encodings•Grammatical–Utilize properties of grammars and computer languages–Subroutines and hierarchy•Cell chemistry–Simulate low-level chemical and biological properties–Diffusion, reaction, growth, signaling, etc.Grammatical Example 1•L-systems: Good for fractal-like structures, plants, highly regular structuresL-System Evolution Successes•Greg Hornby’s Ph.D. dissertation topic (http://ic.arc.nasa.gov/people/hornby)•Clear advantage over direct encodingsGrowth of a TableHornby, G.. S. and Pollack, J. B. The Advantages of Generative Grammatical Encodings for Physical Design. Congress on Evolutionary Computation. 2001.Grammatical Example 2•Cellular Encoding (CE; Gruau 1993, 1996)F. Gruau. Neural network synthesis using cellular encoding and the genetic algorithm. PhD thesis, Laboratoire de L'informatique du Paralllisme, Ecole Normale Supriere de Lyon, Lyon, France, 1994.Cell Chemistry EncodingsCell Chemistry Example: Bongard’s Artificial Ontogeny Bongard, J. C. and R. Pfeifer (2001a) Repeated Structure and Dissociation of Genotypic and Phenotypic Complexity in Artificial Ontogeny, in Spector, L. et al (eds.), Proceedings of The Genetic and Evolutionary Computation Conference, GECCO-2001. San Francisco, CA: Morgan Kaufmann publishers, pp. 829-836. Bongard, J. C. and R. Pfeifer (2003) Evolving Complete Agents Using Artificial Ontogeny, in Hara, F. and R. Pfeifer, (eds.), Morpho-functional Machines: The New Species (Designing Embodied Intelligence) Springer-Verlag, pp. 237-258.Cell Chemistry Example 2•Federici 2004: Neural networks inside cellsMulti-cellular development: is there scalability and robustness to gain?, Daniel Roggen and Diego Federici, in proceedings of PPSN VIII 2004 The 8th International Conference on Parallel Problem Solving from Nature, Xin Yao and al. ed., pp 391-400, (2004).Differences in AE Implementations•Encoding: Grammatical vs. Cell-chemistry•Cell Fate: Final role determined in several ways•Targeting: Special or relative target specification•Canalization: Robustness to small disturbances•Complexification: From fixed-length genomes to expanding genomesCell Fate•Many different ways to determine ultimate role of cell•Cell positioning mechanism can also differ from natureTargeting•How do cells become connected such as in a neural network?•Genes may specify a specific target identity•Or target may be specified through relative position?Heterochrony•The order of concurrent events can vary in nature•When different processes intersect can determine how they coordinateCanalization•Crucial pathways become entrenched in development–Stochasticity–Resource Allocation–OverproductionComplexification through Gene Duplication•Gene Duplication can add new genes in any indirect encoding •Major gene duplication event as vertebrates appeared •New HOX genes elaborated overall developmental pattern •Initially redundant regulatory roles are partitionedGeneral Alignment Problem•Variable length genomes are difficult to alignHistorical Markings (NEAT) Solve the Alignment ProblemExploring the Space of AEHow Can We Learn How Developmental Encoding Works?•Benchmarks–Evolution of pure symmetry–Evolving a specific shape–Evolving a specific connectivity pattern–Flags•Interactive evolution–Like the “spaceship evolution”–Allow human to explore the space of a dev. encoding–Learn principles by seeing how things change, become canalized, etc..•Major application? (In the future…)The Holy Grail•What is the ultimate AE encoding?•First: Evolve a structure with 100,000 parts•Later: 1,000,000+ parts•What is the ultimate AE application?Next Classes•10/4/06:Shafaq Chaudhry•10/9/06: Advanced Topics in Development–Development without development?–Where is dev. encoding useful?–Programming dev. encoding with NEAT•10/11/06: Compositional Pattern Producing