请输入您要查询的百科知识：

　

词条 HyperNEAT
释义

  1. Applications to date

  2. References

  3. External links

Hypercube-based NEAT, or HyperNEAT,[1] is a generative encoding that evolves artificial neural networks (ANNs) with the principles of the widely used NeuroEvolution of Augmented Topologies (NEAT) algorithm.[2] It is a novel technique for evolving large-scale neural networks using the geometric regularities of the task domain. It uses Compositional Pattern Producing Networks [3] (CPPNs), which are used to generate the images for Picbreeder.org and shapes for EndlessForms.com. HyperNEAT has recently been extended to also evolve plastic ANNs [4] and to evolve the location of every neuron in the network.[5]

Applications to date

  • Multi-agent learning[6]
  • Checkers board evaluation[7]
  • Controlling Legged Robots[8][9][10][11][12][13][https://www.youtube.com/watch?v=V2ADU8YWIug video]
  • Comparing Generative vs. Direct Encodings[14][15][16]
  • Investigating the Evolution of Modular Neural Networks[17][18][19]
  • Evolving Objects that can be 3D-printed[20]
  • Evolving the Neural Geometry and Plasticity of an ANN[21]

References

1. ^{{Cite journal|last=Stanley|first=Kenneth O.|last2=D'Ambrosio|first2=David B.|last3=Gauci|first3=Jason|date=2009-01-14|title=A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks|journal=Artificial Life|volume=15|issue=2|pages=185–212|doi=10.1162/artl.2009.15.2.15202|pmid=19199382|issn=1064-5462}}
2. ^{{Cite journal|last=Stanley|first=Kenneth O.|last2=Miikkulainen|first2=Risto|date=2002-06-01|title=Evolving Neural Networks through Augmenting Topologies|journal=Evolutionary Computation|volume=10|issue=2|pages=99–127|doi=10.1162/106365602320169811|issn=1063-6560|pmid=12180173|citeseerx=10.1.1.638.3910}}
3. ^{{Cite journal|last=Stanley|first=Kenneth O.|date=2007-05-10|title=Compositional pattern producing networks: A novel abstraction of development|journal=Genetic Programming and Evolvable Machines|language=en|volume=8|issue=2|pages=131–162|doi=10.1007/s10710-007-9028-8|issn=1389-2576|citeseerx=10.1.1.643.8179}}
4. ^{{Cite book|title=From Animals to Animats 11|last=Risi|first=Sebastian|last2=Stanley|first2=Kenneth O.|date=2010-08-25|publisher=Springer Berlin Heidelberg|isbn=9783642151927|editor-last=Doncieux|editor-first=Stéphane|series=Lecture Notes in Computer Science|pages=533–543|language=en|doi=10.1007/978-3-642-15193-4_50|editor-last2=Girard|editor-first2=Benoît|editor-last3=Guillot|editor-first3=Agnès|editor-last4=Hallam|editor-first4=John|editor-last5=Meyer|editor-first5=Jean-Arcady|editor-last6=Mouret|editor-first6=Jean-Baptiste|citeseerx = 10.1.1.365.5589}}
5. ^{{Cite journal|last=Risi|first=Sebastian|last2=Stanley|first2=Kenneth O.|date=2012-08-31|title=An Enhanced Hypercube-Based Encoding for Evolving the Placement, Density, and Connectivity of Neurons|journal=Artificial Life|volume=18|issue=4|pages=331–363|doi=10.1162/ARTL_a_00071|pmid=22938563|issn=1064-5462}}
6. ^{{Cite book|last=D'Ambrosio|first=David B.|last2=Stanley|first2=Kenneth O.|date=2008-01-01|title=Generative Encoding for Multiagent Learning|journal=Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation|series=GECCO '08|location=New York, NY, USA|publisher=ACM|pages=819–826|doi=10.1145/1389095.1389256|isbn=9781605581309}}
7. ^J. Gauci and K. O. Stanley, “A case study on the critical role of geometric regularity in machine learning,” in AAAI (D. Fox and C. P. Gomes, eds.), pp. 628–633, AAAI Press, 2008.
8. ^{{Cite book|last=Risi|first=Sebastian|last2=Stanley|first2=Kenneth O.|date=2013-01-01|title=Confronting the Challenge of Learning a Flexible Neural Controller for a Diversity of Morphologies|journal=Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation|series=GECCO '13|location=New York, NY, USA|publisher=ACM|pages=255–262|doi=10.1145/2463372.2463397|isbn=9781450319638|citeseerx=10.1.1.465.5068}}
9. ^{{Cite book|last=Clune|first=J.|last2=Beckmann|first2=B. E.|last3=Ofria|first3=C.|last4=Pennock|first4=R. T.|date=2009-05-01|title=Evolving coordinated quadruped gaits with the HyperNEAT generative encoding|journal=2009 IEEE Congress on Evolutionary Computation|pages=2764–2771|doi=10.1109/CEC.2009.4983289|isbn=978-1-4244-2958-5|citeseerx=10.1.1.409.3868}}
10. ^{{Cite book|last=Clune|first=Jeff|last2=Ofria|first2=Charles|last3=Pennock|first3=Robert T.|date=2009-01-01|title=The Sensitivity of HyperNEAT to Different Geometric Representations of a Problem|journal=Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation|series=GECCO '09|location=New York, NY, USA|publisher=ACM|pages=675–682|doi=10.1145/1569901.1569995|isbn=9781605583259}}
11. ^Yosinski J, Clune J, Hidalgo D, Nguyen S, Cristobal Zagal J, Lipson H (2011) Evolving Robot Gaits in Hardware: the HyperNEAT Generative Encoding Vs. Parameter Optimization. Proceedings of the European Conference on Artificial Life. (pdf)
12. ^Lee S, Yosinski J, Glette K, Lipson H, Clune J (2013) Evolving gaits for physical robots with the HyperNEAT generative encoding: the benefits of simulation. Applications of Evolutionary Computing. Springer. pdf
13. ^{{Cite book|title=Applications of Evolutionary Computation|last=Lee|first=Suchan|last2=Yosinski|first2=Jason|last3=Glette|first3=Kyrre|last4=Lipson|first4=Hod|last5=Clune|first5=Jeff|date=2013-04-03|publisher=Springer Berlin Heidelberg|isbn=9783642371912|editor-last=Esparcia-Alcázar|editor-first=Anna I.|series=Lecture Notes in Computer Science|pages=540–549|language=en|doi=10.1007/978-3-642-37192-9_54|citeseerx = 10.1.1.364.8979}}
14. ^{{Cite journal|last=Clune|first=J.|last2=Stanley|first2=K. O.|last3=Pennock|first3=R. T.|last4=Ofria|first4=C.|date=2011-06-01|title=On the Performance of Indirect Encoding Across the Continuum of Regularity|journal=IEEE Transactions on Evolutionary Computation|volume=15|issue=3|pages=346–367|doi=10.1109/TEVC.2010.2104157|issn=1089-778X|citeseerx=10.1.1.375.6731}}
15. ^{{Cite book|title=Parallel Problem Solving from Nature – PPSN X|last=Clune|first=Jeff|last2=Ofria|first2=Charles|last3=Pennock|first3=Robert T.|date=2008-09-13|publisher=Springer Berlin Heidelberg|isbn=9783540876991|editor-last=Rudolph|editor-first=Günter|series=Lecture Notes in Computer Science|pages=358–367|language=en|doi=10.1007/978-3-540-87700-4_36|editor-last2=Jansen|editor-first2=Thomas|editor-last3=Beume|editor-first3=Nicola|editor-last4=Lucas|editor-first4=Simon|editor-last5=Poloni|editor-first5=Carlo}}
16. ^{{Cite book|title=Advances in Artificial Life. Darwin Meets von Neumann|last=Clune|first=Jeff|last2=Beckmann|first2=Benjamin E.|last3=Pennock|first3=Robert T.|last4=Ofria|first4=Charles|date=2009-09-13|publisher=Springer Berlin Heidelberg|isbn=9783642213137|editor-last=Kampis|editor-first=George|series=Lecture Notes in Computer Science|pages=134–141|language=en|doi=10.1007/978-3-642-21314-4_17|editor-last2=Karsai|editor-first2=István|editor-last3=Szathmáry|editor-first3=Eörs|citeseerx = 10.1.1.409.741}}
17. ^{{Cite book|last=Clune|first=Jeff|last2=Beckmann|first2=Benjamin E.|last3=McKinley|first3=Philip K.|last4=Ofria|first4=Charles|date=2010-01-01|title=Investigating Whether hyperNEAT Produces Modular Neural Networks|journal=Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation|series=GECCO '10|location=New York, NY, USA|publisher=ACM|pages=635–642|doi=10.1145/1830483.1830598|isbn=9781450300728|citeseerx=10.1.1.409.4870}}
18. ^{{Cite book|last=Suchorzewski|first=Marcin|last2=Clune|first2=Jeff|date=2011-01-01|title=A Novel Generative Encoding for Evolving Modular, Regular and Scalable Networks|journal=Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation|series=GECCO '11|location=New York, NY, USA|publisher=ACM|pages=1523–1530|doi=10.1145/2001576.2001781|isbn=9781450305570|citeseerx=10.1.1.453.5744}}
19. ^{{Cite book|last=Verbancsics|first=Phillip|last2=Stanley|first2=Kenneth O.|date=2011-01-01|title=Constraining Connectivity to Encourage Modularity in HyperNEAT|journal=Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation|series=GECCO '11|location=New York, NY, USA|publisher=ACM|pages=1483–1490|doi=10.1145/2001576.2001776|isbn=9781450305570|citeseerx=10.1.1.379.1188}}
20. ^{{Cite journal|last=Clune|first=Jeff|last2=Lipson|first2=Hod|date=2011-11-01|title=Evolving 3D Objects with a Generative Encoding Inspired by Developmental Biology|journal=SIGEVOlution|volume=5|issue=4|pages=2–12|doi=10.1145/2078245.2078246|issn=1931-8499}}
21. ^{{Cite book|last=Risi|first=S.|last2=Stanley|first2=K. O.|date=2012-06-01|title=A unified approach to evolving plasticity and neural geometry|journal=The 2012 International Joint Conference on Neural Networks (IJCNN)|pages=1–8|doi=10.1109/IJCNN.2012.6252826|isbn=978-1-4673-1490-9|citeseerx=10.1.1.467.8366}}
{{bioinformatics-stub}}

External links

  • HyperNEAT Users Page
  • Ken Stanley's website
  • "Evolutionary Complexity Research Group at UCF"
  • NEAT Project Homepage
  • PicBreeder.org
  • EndlessForms.com
  • BEACON Blog: What is neuroevolution?

4 : Artificial neural networks|Evolutionary algorithms|Evolutionary computation|Genetic algorithms
随便看

　

开放百科全书收录14589846条英语、德语、日语等多语种百科知识，基本涵盖了大多数领域的百科知识，是一部内容自由、开放的电子版国际百科全书。

　

Copyright © 2023 OENC.NET All Rights Reserved
京ICP备2021023879号 更新时间：2024/11/11 10:04:07