Abstract
HyperNEAT, which stands for Hypercube-based NeuroEvolution of Augmenting Topologies, is a method for evolving indirectly-encoded artificial neural networks (ANNs) that was first introduced in 2007. By exploiting a unique indirect encoding called Compositional Pattern Producing Networks (CPPNs) that does not require a typical developmental stage, HyperNEAT introduced several novel capabilities to the field of neuroevolution (i.e. evolving artificial neural networks). Among these, (1) large ANNs can be compactly encoded by small genomes, (2) the size and resolution of evolved ANNs can scale up or down even after training is completed, and (3) neural structure can be evolved to exploit problem geometry. Five years after its introduction, researchers have leveraged these capabilities to produce a broad range of successful experiments and extensions that highlight the potential for future research to build further on the ideas introduced by HyperNEAT. This chapter reviews these first 5 years of research that builds upon this approach, and culminates with thoughts on promising future directions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
T. Aaltonen et al., (over 100 authors). Measurement of the top quark mass with dilepton events selected using neuroevolution at CDF. Phys. Rev. Lett. 102(15), 2001 (2009)
L. Altenberg, Evolving better representations through selective genome growth. in Proceedings of the IEEE World Congress on Computational Intelligence (IEEE Press, Piscataway, NJ, 1994), pp. 182–187
P.J. Angeline, G.M. Saunders, J.B. Pollack, An evolutionary algorithm that constructs recurrent neural networks. IEEE Trans. Neural Networks 5, 54–65 (1993)
J.E. Auerbach, J.C. Bongard, Dynamic resolution in the co-evolution of morphology and control. in Proceedings of the 12th International Conference on the Synthesis and Simulation of Living Systems (ALife XII) (2010)
J.E. Auerbach, J.C. Bongard, Evolving CPPNs to grow three dimensional structures. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2010) (ACM Press, New York, NY, 2010)
J.E. Auerbach, J.C. Bongard, Evolving complete robots with CPPN-NEAT: the utility of recurrent connections. in Proceedings of the 13th Annual Conference Companion on Genetic and Evolutionary Computation (ACM, 2011)
J.E. Auerbach, J.C. Bongard, On the relationship between environmental and mechanical complexity in evolved robots. in 13th International Conference on the Synthesis and Simulation of Living Systems (ALife XIII) (ACM, 2012)
J.E. Auerbach, J.C. Bongard, On the relationship between environmental and morphological complexity in evolved robots. in Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation (ACM, 2012)
E. Bahceci, R. Miikkulainen, Transfer of evolved pattern-based heuristics in games. in Proceedings of the IEEE Symposium on Computational Intelligence and Games (CIG-2008) (IEEE Press, Piscataway, NJ, 2008)
R.D. Beer, J.C. Gallagher, Evolving dynamical neural networks for adaptive behavior. Adapt. behav. 1(1), 91–122 (1992)
P.J. Bentley, S. Kumar, Three ways to grow designs: a comparison of embryogenies for an evolutionary design problem. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-1999) (1999), pp. 35–43
J. Blynel, D. Floreano, Levels of dynamics and adaptive behavior in evolutionary neural controllers. in Proceedings of the Seventh International Conference on Simulation of Adaptive Behavior on From Animals to Animats (2002), pp. 272–281
J.C. Bongard, Evolving modular genetic regulatory networks. in Proceedings of the 2002 Congress on Evolutionary Computation (2002)
Z. Buk, J. Koutník, M. Šnorek, NEAT in HyperNEAT substituted with genetic programming. in Adaptive and Natural Computing Algorithms (2009), pp. 243–252
D.B. Chklovskii, A.A. Koulakov, Maps in the brain: what can we learn from them? Annu. Rev. Neurosci. 27, 369–392 (2004)
P.M. Churchland, Some reductive strategies in cognitive neurobiology. Mind 95, 279–309 (1986)
J. Clune, B.E. Beckmann, P.K. McKinley, C. Ofria, Investigating whether HyperNEAT produces modular neural networks. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2010) (ACM Press, New York, NY, 2010)
J. Clune, C. Ofria, R.T. Pennock, How a generative encoding fares as problem-regularity decreases. in Proceedings of the 10th International Conference on Parallel Problem Solving From Nature (PPSN 2008) (Springer, Berlin, 2008), pp. 258–367
J. Clune, R.T. Pennock, C. Ofria. The sensitivity of HyperNEAT to different geometric representations of a problem. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2009) (ACM Press, New York, NY, USA, 2009)
J. Clune, K.O. Stanley, R.T. Pennock, C. Ofria, On the performance of indirect encoding across the continuum of regularity. IEEE Trans. Evol. Comput. 15(3), 346–367 (2011)
J. Clune, K.O. Stanley, R.T. Pennock, C. Ofria, On the performance of indirect encoding across the continuum of regularity. IEEE Trans. Evol. Comput. 15(3), 346–367 (2011)
O.J. Coleman et al., Evolving neural networks for visual processing. Ph.D. thesis, BS Thesis. The University of New South Wales, 2010
D.B. D’Ambrosio, S. Goodell, J. Lehman, S. Risi, K.O. Stanley, Multirobot Behavior Synchronization Through Direct Neural Network Communication (Springer, New York, 2012)
D.B. D’Ambrosio, J. Lehman, S. Risi, K.O. Stanley, Evolving policy geometry for scalable multiagent learning. in Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2010) (International Foundation for Autonomous Agents and Multiagent System, 2010), pp. 731–738
D.B. D’Ambrosio, J. Lehman, S. Risi, K.O. Stanley, Task switching in multiagent learning through indirect encoding. in Proceedings of the International Conference on Intelligent Robots and Systems (IROS 2011) (IEEE, Piscataway, NJ, 2011)
D.B. D’Ambrosio, K.O. Stanley, A novel generative encoding for exploiting neural network sensor and output geometry. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2007) (ACM Press, New York, NY, 2007)
D.B. D’Ambrosio, K.O. Stanley, Generative encoding for multiagent learning. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2008) (ACM Press, New York, NY, 2008)
F. Dellaert, Toward a biologically defensible model of development. Master’s thesis, Case Western Reserve University, Clevekand, OH, 1995
P. Deloukas, G.D. Schuler, G. Gyapay, E.M. Beasley, C. Soderlund, P. Rodriguez-Tome, L. Hui, T.C. Matise, K.B. McKusick, J.S. Beckmann, S. Bentolila, M. Bihoreau, B.B. Birren, J. Browne, A. Butler, A.B. Castle, N. Chiannilkulchai, C. Clee, P.J. Day, A. Dehejia, T. Dibling, N. Drouot, S. Duprat, C. Fizames, D.R. Bentley, A physical map of 30,000 human genes. Science 282(5389), 744–746 (1998)
J. Drchal, O. Kapra, J. Koutnik, M. Snorek, Combining multiple inputs in HyperNEAT mobile agent controller. in 19th International Conference on Artificial Neural Networks (ICANN 2009) (Berlin, Springer, 2009), pp. 775–783
J. Drchal, J. Koutnik, M. Snorek, HyperNEAT controlled robots learn to drive on roads in simulated environment. in Proceedings of the IEEE Congress on Evolutionary Computation (CEC-2009) (IEEE Press, Piscataway, NJ, USA, 2009)
P. Eggenberger, Evolving Morphologies of Simulated 3D Organisms Based on Differential Gene Expression (MIT Press, Boston, 1997), pp. 205–213
D. Floreano, P. Dürr, C. Mattiussi, Neuroevolution: from architectures to learning. Evol. Intell. 1, 47–62 (2008)
D. Floreano, J. Urzelai, Evolutionary robots with on-line self-organization and behavioral fitness. Neural Netw. 13, 431–4434 (2000)
J. Gauci, K.O. Stanley, Generating large-scale neural networks through discovering geometric regularities. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2007) (ACM Press, New York, NY, 2007)
J. Gauci, K.O. Stanley, Autonomous evolution of topographic regularities in artificial neural networks. Neural Comput. 22(7), 1860–1898 (2010)
J. Gauci, K.O. Stanley, Indirect encoding of neural networks for scalable go. in Proceedings of the 11th International Conference on Parallel Problem Solving From Nature (PPSN-2010) (Springer, 2011), pp. 354–363
C.D. Gilbert, T.N. Wiesel, Receptive field dynamics in adult primary visual cortex. Nature 356, 150–152 (1992)
F. Gomez, R. Miikkulainen, Incremental evolution of complex general behavior. Adapt. Behav. 5, 317–342 (1997)
F. Gomez, R. Miikkulainen, Solving non-Markovian control tasks with neuroevolution (1999), pp. 1356–1361
G.J. Goodhill, M.A. Carreira-Perpinn, Cortical Columns, in Encyclopedia of Cognitive Science, volume 1, ed. by L. Nadel (MacMillan Publishers Ltd., London, 2002), pp. 845–851
F. Gruau, D. Whitley, L. Pyeatt, in A Comparison Between Cellular Encoding and Direct Encoding for Genetic Neural Networks, ed. by R. John Koza, D.E. Goldberg, D.B. Fogel, R.L. Riolo. Genetic Programming 1996: Proceedings of the First Annual Conference (MIT Press, 1996), pp. 81–89
E. Haasdijk, A.A. Rusu, A.E. Eiben, HyperNEAT for locomotion control in modular robots. in Proceedings of the 9th International Conference on Evolvable Systems (ICES 2010) (2010)
I. Harvey, The artificial evolution of adaptive behavior. Ph.D. thesis, School of Cognitive and Computing Sciences, University of Sussex, Sussex, 1993
E. Hastings, R. Guha, K.O. Stanley, Evolving content in the galactic arms race video game. in Proceedings of the IEEE Symposium on Computational Intelligence and Games (CIG-09) (IEEE Press, Piscataway, NJ, 2009)
E.J. Hastings, R.K. Guha, K.O. Stanley, Automatic content generation in the galactic arms race video game. IEEE Trans. Comput. Intell. AI Games 1(4), 245–263 (2010)
J.D. Hiller, H. Lipson, Evolving amorphous robots. in Proceedings of the Twelfth International Conference on Artificial Life (ALIFE XII) (2010)
A.K. Hoover, Michael P. Rosario, K.O. Stanley, in Scaffolding for Interactively Evolving Novel Drum Tracks for Existing Songs, ed. by M. Giacobini. Proceedings of the Sixth European Workshop on Evolutionary and Biologically Inspired Music, Sound, Art and Design (EvoMUSART 2008) (Springer, March 2008), pp. 412–422
A.K. Hoover, K.O. Stanley, Exploiting functional relationships in musical composition. Connect. Sci. Spec. Issue Music Brain Cogn. 21(2 and 3), 227–251 (2009)
G.S. Hornby, J.B. Pollack, Creating high-level components with a generative representation for body-brain evolution. Artif. Life 8(3), 223–246 (2002)
D.H. Hubel, T.N. Wiesel, Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J. Neurophysiol. 28, 229–289 (1965)
W. Jaskowski, K. Krawiec, B. Wieloch, Neurohunter-an entry for the balanced diet contest (2008)
E.R. Kandel, J.H. Schwartz, T.M. Jessell, Principles of Neural Science, 3rd edn. (Elsevier, New York, 1991)
N. Kashtan, U. Alon, Spontaneous evolution of modularity and network motifs. Proc. Nat. Acad. Sci. U.S.A. 102(39), 13773 (2005)
D.B. Knoester, H.J. Goldsby, P.K. McKinley, Neuroevolution of mobile ad hoc networks. in Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation (ACM, 2010), pp. 603–610
N. Kohl, K.O. Stanley, R. Miikkulainen, M. Samples, R. Sherony, Evolving a real-world vehicle warning system. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2006) (July 2006), pp. 1681–1688
J. Lehman, S. Risi, D.B. D’Ambrosio, K.O. Stanley, Rewarding Reactivity to Evolve Robust Controllers Without Multiple Trials or Noise (MIT Press, Cambridge, 2012)
J. Lehman, K.O. Stanley, Abandoning objectives: evolution through the search for novelty alone. Evol. Comput. 19(2), 189–223 (2011)
A. Liapis, G.N. Yannakakis, J. Togelius, Optimizing visual properties of game content through neuroevolution. in Seventh Artificial Intelligence and Interactive Digital Entertainment Conference (2011)
A. Lindenmayer, Adding Continuous Components to L-Systems, in Lecture Notes in Computer Science 15, ed. by G. Rozenberg, A. Salomaa (Springer, Heidelberg, 1974), pp. 53–68
J. Lowell, S. Grabkovsky, K. Birger, Comparison of NEAT and HyperNEAT performance on a strategic decision-making problem. in Fifth International Conference on Genetic and Evolutionary Computing (ICGEC) 2011 (IEEE, 2011), pp. 102–105
W. Maass, C.M. Bishop, Pulsed Neural Networks (The MIT Press, Cambridge, 2001)
A.P. Martin, Increasing genomic complexity by gene duplication and the origin of vertebrates. Am. Nat. 154(2), 111–128 (1999)
J.F. Miller, Evolving a self-repairing, self-regulating, French flag organism. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2004) (Springer, Berlin, 2004)
R.A. Raff, The Shape of Life: Genes, Development, and the Evolution of Animal Form (The University of Chicago Press, Chicago, 1996)
S. Risi, K.O. Stanley, Indirectly encoding neural plasticity as a pattern of local rules. in Proceedings of the 11th International Conference on Simulation of Adaptive Behavior (SAB2010) (Springer, Berlin, 2010)
S. Risi, K.O. Stanley, Enhancing ES-HyperNEAT to evolve more complex regular neural networks. in GECCO ’11: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation (2011)
S. Risi, K.O. Stanley, An enhanced hypercube-based encoding for evolving the placement, density and connectivity of neurons. Artif. Life 18(4), 331–363 (2012)
S. Risi, K.O. Stanley, A Unified Approach to Evolving Plasticity and Neural Geometry (IEEE, Piscataway, 2012)
S. Risi, S.D. Vanderbleek, C.E. Hughes, K.O. Stanley, How novelty search escapes the deceptive trap of learning to learn. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2009) (ACM Press, New York, NY, USA, 2009)
N. Saravanan, D.B. Fogel, Evolving neural control systems. IEEE Expert 10(3), 23–27 (1995)
J. Secretan, N. Beato, D.B. D’Ambrosio, A. Rodriguez, A. Campbell, J.T. Folsom-Kovarik, K.O. Stanley, Picbreeder: a case study in collaborative evolutionary exploration of design space. Evol. Comput. 19(3), 345–371 (2011)
J. Secretan, N. Beato, D.B. D’Ambrosio, A. Rodriguez, A. Campbell, K.O. Stanley, Picbreeder: evolving pictures collaboratively online. in CHI ’08: Proceedings of the Twenty-Sixth Annual SIGCHI Conference on Human Factors in Computing Systems (ACM, New York, NY, USA, 2008), pp. 1759–1768
K. Sims, Evolving 3D Morphology and Behavior by Competition (MIT Press, Cambridge, MA, 1994), pp. 28–39
K.O. Stanley, Exploiting regularity without development. in Proceedings of the AAAI Fall Symposium on Developmental Systems (AAAI Press, Menlo Park, CA, 2006)
K.O. Stanley, Compositional pattern producing networks: a novel abstraction of development. Genet. Program. Evolvable Mach. Spec. Issue Dev. Syst. 8(2), 131–162 (2007)
K.O. Stanley, B.D. Bryant, R. Miikkulainen, Evolving neural network agents in the NERO video game. in Proceedings of the IEEE 2005 Symposium on Computational Intelligence and Games (2005)
K.O. Stanley, B.D. Bryant, R. Miikkulainen, Real-time neuroevolution in the NERO video game. IEEE Trans. Evol. Comput. Spec. Issue Evol. Comput. Games 9(6), 653–668 (2005)
K.O. Stanley, D.B. D’Ambrosio, J. Gauci, A hypercube-based indirect encoding for evolving large-scale neural networks. Artif. Life 15(2), 185–212 (2009)
K.O. Stanley, N. Kohl, R. Miikkulainen, Neuroevolution of an automobile crash warning system. in Proceedings of the Genetic and Evolutionary Computation Conference (2005)
K.O. Stanley, R. Miikkulainen, Efficient reinforcement learning through evolving neural network topologies. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002) (2002)
K.O. Stanley, R. Miikkulainen, Evolving neural networks through augmenting topologies. Evol. Comput. 10, 99–127 (2002)
K.O. Stanley, R. Miikkulainen, A taxonomy for artificial embryogeny. Artif. Life 9(2), 93–130 (2003)
K.O. Stanley, R. Miikkulainen, Competitive coevolution through evolutionary complexification. J. Artif. Intell. Res. 21, 63–100 (2004)
K.O. Stanley, R. Miikkulainen, Evolving a roving eye for go. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2004) (Springer, Berlin, 2004)
M.E. Taylor, S. Whiteson, P. Stone, Comparing evolutionary and temporal difference methods in a reinforcement learning domain. in GECCO 2006: Proceedings of the Genetic and Evolutionary Computation Conference (July 2006), pp. 1321–1328
L. Trujillo, G. Olague, E. Lutton, F.F. de Vega, Discovering Several Robot Behaviors, through Speciation. Applications of Evolutionary Computing: Evoworkshops, Evocomnet. Evofin, Evohot, Evoiasp, Evomusart, Evonum, Evostoc, and Evotranslog (2008), p. 164
P. Verbancsics, K.O. Stanley, Evolving static representations for task transfer. J. Mach. Learn. Res. (JMLR) 11, 1737–1769 (2010)
P. Verbancsics, K.O. Stanley, Task transfer through indirect encoding. in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2010) (ACM Press, New York, NY, 2010)
P. Verbancsics, K.O. Stanley, Constraining connectivity to encourage modularity in HyperNEAT. in Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation (ACM, 2011), pp. 1483–1490
J.D. Watson, N.H. Hopkins, J.W. Roberts, J.A. Steitz, A.M. Weiner, Molecular Biology of the Gene, 4th edn. (The Benjamin Cummings Publishing Company Inc, Menlo Park, 1987)
D.J. Willshaw, C. Von Der Malsburg, How patterned neural connections can be set up by self-organization. Proc. R. Soc. Lond. B Biol. Sci. 194(1117), 431–445 (1976)
D.H. Wolpert, W. Macready, No free lunch theorems for optimization. IEEE Trans. Evol. Comput. 1, 67–82 (1997)
B. Woolley, K.O. Stanley, Evolving a single scalable controller for an octopus arm with a variable number of segments. in Proceedings of the 11th International Conference on Parallel Problem Solving From Nature (PPSN-2010) (Springer, 2011), pp. 270–279
B.G. Woolley, K.O. Stanley, On the deleterious effects of a priori objectives on evolution and representation. in GECCO ’11: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation (2011)
X. Yao, Evolving artificial neural networks. Proc. IEEE 87(9), 1423–1447 (1999)
J. Yosinski, J. Clune, D. Hidalgo, S. Nguyen, J.C. Zagal, H. Lipson, Generating gaits for physical quadruped robots: evolved neural networks vs. local parameterized search. in Proceedings of the 13th Annual Conference Companion on Genetic and Evolutionary Computation (ACM, 2011), pp. 31–32
M.J. Zigmond, F.E. Bloom, S.C. Landis, J.L. Roberts, L.R. Squire (eds.), Fundamental Neuroscience (Academic Press, London, 1999)
Acknowledgments
Much of the work on HyperNEAT at the Evolutionary Complexity Research Group at the University of Central Florida was supported by DARPA through its Computer Science Study Group program, including Phases 1, 2, and 3 (grants HR0011- 08-1-0020, HR0011-09-1-0045 and N11AP20003). This chapter does not necessarily reflect the position or policy of the government, and no official endorsement should be inferred.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: Implementations
Appendix: Implementations
Many researchers mentioned above have made their implementations of HyperNEAT available:
-
HyperSharpNEAT by David D’Ambrosio is an extension of Colin Green’s SharpNEAT1, which is written in C#. HyperSharpNEAT contains an implementation of multiagent HyperNEAT and has been augmented by Joel Lehman and Sebastian Risi to contain the LEO, ES, and adaptive HyperNEAT extensions.
-
SharpNEAT2 by Colin Green, which includes a different version of HyperNEAT, is also written in C# and contains several example experiments as well as tutorials on making new ones.
-
Keepaway HyperNEAT C# by Philip Verbancsics is distributed with a C# implementation of the Robocup simulator.
-
Another HyperNEAT Implementation (ANHI) by Oliver Coleman extends the Java-based ANJI implementation of NEAT (itself by Derek James and Philip Tucker). AHNI includes several visual processing experiments.
-
HyperNEAT C++ by Jason Gauci comes with visual discrimination and checkers experiments.
Links to all these software packages can be found at http://eplex.cs.ucf.edu/hyperNEATpage/.
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
D’Ambrosio, D.B., Gauci, J., Stanley, K.O. (2014). HyperNEAT: The First Five Years. In: Kowaliw, T., Bredeche, N., Doursat, R. (eds) Growing Adaptive Machines. Studies in Computational Intelligence, vol 557. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-55337-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-55337-0_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-55336-3
Online ISBN: 978-3-642-55337-0
eBook Packages: EngineeringEngineering (R0)