NEAT: Evolving Increasingly Complex Neural Network Topologies
Active from 2000 - 2011
Many neuroevolution methods evolve fixed-topology networks. Some methods evolve topologies in addition to weights, but these usually have a bound on the complexity of networks that can be evolved and begin evolution with random topologies. This project is based on a neuroevolution method called NeuroEvolution of Augmenting Topologies (NEAT) that can evolve networks of unbounded complexity from a minimal starting point. The initial stage of research aims to demonstrate that topology can be used to increase the efficiency of search if it minimizes the dimensionality of the weight space. We performed several pole balancing experiments that demonstrate that evolving topology using NEAT indeed provides an advantage. However, the research has a broader goal of showing that evolving topologies is necessary to achieve 3 major goals of neuroevolution: (1) Continual coevolution: Successful competitive coevolution can use the evolution of topologies to continuously elaborate strategies. (2) Evolution of Adaptive Networks: The evolution of topologies allows neuroevolution to evolve adaptive networks with plastic synapses by designating which connections should be adaptive and in what ways. (3) Combining Expert Networks: Separate expert neural networks can be fused through the evolution of connecting neurons between them. Because we want to show that growing structure is necessary to achieve these goals, it is important that an efficient and principled method for evolving topologies is available for experimentation. NEAT provides just such an experimental platform. NEAT is also an important contribution to GAs because it shows how it is possible for evolution to both optimize and complexify solutions simultaneously, making it possible to evolve increasingly complex solutions over time, thereby strengthening the analogy with biological evolution.
  • On the NEAT Method: Evolutionary Computation Journal Paper and a Conference Paper (Best Paper Award Winner at GECCO-2002) that goes into discussion of the way NEAT performs search.
    A shorter second Conference Paper on improving NE efficiency with evolution of topologies, emphasizing ablation studies.
  • NEAT User Information: NEAT Users Page includes a FAQ.
  • On the benefits of Complexification: A Conference Paper on using the complexification of networks to enhance the performance of competitive coevolution. A more extensive and general Journal Paper (new) about complexification. The NEAT Demo Page includes animated GIF movie clips of simulated robot controllers coevolved using NEAT.
  • Software: NEAT Software is available in C++, Java, and Matlab source code (see below)
  • On Analyzing Results: Our papers on complexification utilized a method that we developed for monitoring progress in coevolution called Dominance Tournament.
  • Artificial Embryogeny: Journal Paper on evolving structures that develop from a single cell. A shorter symposium paper on combining complexification with indirect encodings.
  • Evolving Hebbian Networks: Conference Paper comparing the evolution of networks with dynamic and static synapses.
Kenneth Stanley Postdoctoral Alumni kstanley [at] cs ucf edu
Shimon Whiteson Formerly affiliated Collaborator s a whiteson [at] uva nl
Joseph Reisinger Ph.D. Alumni joeraii [at] cs utexas edu
Igor V. Karpov Ph.D. Student ikarpov [at] gmail com
Nate Kohl Ph.D. Alumni nate [at] natekohl net
     [Expand to show all 24][Minimize]
Acquiring Evolvability through Adaptive Representations 2007
Joseph Reisinger and Risto Miikkulainen, In Proceeedings of the Genetic and Evolutionary Computation Conference, pp. 1045-1052 2007.
Coevolving Strategies for General Game Playing 2007
Joseph Reisinger, Erkin Bahceci, Igor Karpov and Risto Miikkulainen, In Proceedings of the {IEEE} Symposium on Computational Intelligence and Games, pp. 320-327, Piscataway, NJ 2007. IEEE.
Coevolution of Neural Networks using a Layered Pareto Archive 2006
German A. Monroy, Kenneth O. Stanley, Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference, pp. 329-336, Seattle, Washington, July 2006. New York, NY: ACM Press.
Computational Intelligence in Games 2006
Risto Miikkulainen, Bobby D. Bryant, Ryan Cornelius, Igor V. Karpov, Kenneth O. Stanley, and Chern Han Yong, In Computational Intelligence: Principles and Practice, Gary Y. Yen and David B. Fogel (Eds.), Piscataway, NJ 2006. IEEE Computational Intelligence Society.
Creating Intelligent Agents in Games 2006
Risto Miikkulainen, The Bridge (2006), pp. 5-13.
Real-Time Evolution of Neural Networks in the NERO Video Game 2006
Kenneth O. Stanley, Bobby D. Bryant, Igor Karpov, Risto Miikkulainen, In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI-2006), pp. 1671--1674, Boston, MA 2006. Meno Park, CA: AAAI Press.
Evolving Neural Network Agents in the NERO Video Game 2005
Kenneth O. Stanley, Bobby D. Bryant, and Risto Miikkulainen, In Proceedings of the IEEE 2005 Symposium on Computational Intelligence and Games (CIG'05), Piscataway, NJ 2005. IEEE.
Incorporating Advice into Evolution of Neural Networks 2005
Chern Han Yong, Kenneth O. Stanley, and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2005) 2005. Late Breaking Papers.
Neuroevolution of an Automobile Crash Warning System 2005
Kenneth Stanley, Nate Kohl, Rini Sherony, and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference 2005.
Real-Time Learning in the NERO Video Game 2005
Kenneth O. Stanley, Ryan Cornelius, Risto Miikkulainen, Thomas D'Silva, and Aliza Gold, In Proceedings of the Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE 2005) Demo Papers 2005.
Real-time Neuroevolution in the NERO Video Game 2005
Kenneth O. Stanley, Bobby D. Bryant, and Risto Miikkulainen, IEEE Transactions on Evolutionary Computation (2005), pp. 653-668. IEEE.
Retaining Learned Behavior During Real-Time Neuroevolution 2005
Thomas D'Silva, Roy Janik, Michael Chrien, Kenneth O. Stanley and Risto Miikkulainen, Artificial Intelligence and Interactive Digital Entertainment (2005). American Association for Artificial Intelligence.
Towards an Empirical Measure of Evolvability 2005
Joseph Reisinger, Kenneth O. Stanley, Risto Miikkulainen, In Genetic and Evolutionary Computation Conference {(GECCO2005)} Workshop Program, pp. 257-264, Washington, D.C. 2005. ACM Press.
Competitive Coevolution through Evolutionary Complexification 2004
Kenneth O. Stanley and Risto Miikkulainen, Journal of Artificial Intelligence Research, Vol. 21 (2004), pp. 63-100.
Evolving a Roving Eye for Go 2004
Kenneth O. Stanley and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2004), Berlin 2004. Springer Verlag.
Evolving Reusable Neural Modules 2004
Joseph Reisinger, Kenneth O. Stanley, and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference 2004.
A Taxonomy for Artificial Embryogeny 2003
Kenneth O. Stanley and Risto Miikkulainen, Artificial Life, Vol. 9, 2 (2003), pp. 93-130.
Achieving High-Level Functionality through Evolutionary Complexification 2003
Kenneth O. Stanley and Risto Miikkulainen, In Proceedings of the AAAI-2003 Spring Symposium on Computational Synthesis, Stanford, CA 2003. AAAI Press.
Evolving Adaptive Neural Networks with and Without Adaptive Synapses 2003
Kenneth O. Stanley, Bobby D. Bryant, and Risto Miikkulainen, In Proceedings of the 2003 Congress on Evolutionary Computation, Piscataway, NJ 2003. IEEE.
Continual Coevolution Through Complexification 2002
Kenneth O. Stanley and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002), William B. Langdon and Erick Cantu-Paz and Keith E. Mathias and Rajkumar Roy and David Davis and Riccardo Pol...
Efficient Evolution Of Neural Network Topologies 2002
Kenneth O. Stanley and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference, William B. Langdon and Erick Cantu-Paz and Keith E. Mathias and Rajkumar Roy and David Davis and Riccardo Poli and Karthik...
Efficient Reinforcement Learning Through Evolving Neural Network Topologies 2002
Kenneth O. Stanley and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002), pp. 9, San Francisco 2002. Morgan Kaufmann.
Evolving Neural Networks Through Augmenting Topologies 2002
Kenneth O. Stanley and Risto Miikkulainen, Evolutionary Computation, Vol. 10, 2 (2002), pp. 99-127.
The Dominance Tournament Method of Monitoring Progress in Coevolution 2002
Kenneth O. Stanley and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference ({GECCO}-2002) Workshop Program, pp. 7, San Francisco 2002. Morgan Kaufmann.
NEAT C++ The NEAT package contains source code implementing the NeuroEvolution of Augmenting Topologies method. The source code i... 2010

OpenNERO OpenNERO is a general research and education platform for artificial intelligence. The platform is based on a simulatio... 2010

rtNEAT C++ The rtNEAT package contains source code implementing the real-time NeuroEvolution of Augmenting Topologies method. In ad... 2006

NEAT: ANJI (Another NEAT Java Implementation) The ANJI package contains Java source code for the NeuroEvolution of Augmenting Topologies method (see the original 2004

NEAT C# The SharpNEAT package contains C# source code for the NeuroEvolution of Augmenting Topologies method (see the original <... 2003

NEAT Delphi The Delphi NEAT package contains Delphi source code for the NeuroEvolution of Augmenting Topologies method (see the orig... 2003

NEAT Matlab The Matlab NEAT package contains Matlab source code for the NeuroEvolution of Augmenting Topologies method (see the orig... 2003

NEAT C++ for Microsoft Windows The Windows NEAT package contains C++ source code for the NeuroEvolution of Augmenting Topologies method (see the origin... 2002

NEAT Java (JNEAT) The JNEAT package contains Java source code for the NeuroEvolution of Augmenting Topologies method (see the original 2002