Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Designing neural networks through neuroevolution


Much of recent machine learning has focused on deep learning, in which neural network weights are trained through variants of stochastic gradient descent. An alternative approach comes from the field of neuroevolution, which harnesses evolutionary algorithms to optimize neural networks, inspired by the fact that natural brains themselves are the products of an evolutionary process. Neuroevolution enables important capabilities that are typically unavailable to gradient-based approaches, including learning neural network building blocks (for example activation functions), hyperparameters, architectures and even the algorithms for learning themselves. Neuroevolution also differs from deep learning (and deep reinforcement learning) by maintaining a population of solutions during search, enabling extreme exploration and massive parallelization. Finally, because neuroevolution research has (until recently) developed largely in isolation from gradient-based neural network research, it has developed many unique and effective techniques that should be effective in other machine learning areas too. This Review looks at several key aspects of modern neuroevolution, including large-scale computing, the benefits of novelty and diversity, the power of indirect encoding, and the field’s contributions to meta-learning and architecture search. Our hope is to inspire renewed interest in the field as it meets the potential of the increasing computation available today, to highlight how many of its ideas can provide an exciting resource for inspiration and hybridization to the deep learning, deep reinforcement learning and machine learning communities, and to explain how neuroevolution could prove to be a critical tool in the long-term pursuit of artificial general intelligence.

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Rent or buy this article

Prices vary by article type



Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Compositional pattern-producing networks and HyperNEAT.
Fig. 2: Sample evolved topologies of modules for the Omniglot multitask learning benchmark.


  1. Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning (MIT Press, Cambridge, 2016).

  2. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

    Article  Google Scholar 

  3. Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015).

    Article  Google Scholar 

  4. Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction (MIT Press, Cambridge, 2018).

  5. Rumelhart, D. E., Hinton, G. E. & Williams, R. J. Learning representations by back-propagating errors. Nature 323, 533–536 (1986).

    Article  Google Scholar 

  6. De Jong, K. A. Evolutionary Computation: A Unified Perspective (MIT Press, Cambridge, 2002).

    Google Scholar 

  7. Gruau, F. Automatic definition of modular neural networks. Adapt. Behav. 3, 151–183 (1994).

    Article  Google Scholar 

  8. Yao, X. A review of evolutionary artificial neural networks. Int. J. Intell. Syst. 8, 539–567 (1993).

    Article  Google Scholar 

  9. Floreano, D., Dürr, P. & Mattiussi, C. Neuroevolution: from architectures to learning. Evol. Intell. 1, 47–62 (2008).

    Article  Google Scholar 

  10. Soltoggio, A., Stanley, K. O. & Risi, S. Born to learn: the inspiration, progress, and future of evolved plastic artificial neural networks. Neural Netw. 108, 48–67 (2018).

    Article  Google Scholar 

  11. Dasgupta, D. & McGregor, D. Designing application-specific neural networks using the structured genetic algorithm. In Proc. COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks 87–96 (IEEE, 1992).

  12. Pujol, J. C. F. & Poli, R. Evolving the topology and the weights of neural networks using a dual representation. Appl. Intell. J. 8, 73–84 (1998).

    Article  Google Scholar 

  13. Bongard, J. C. & Pfeifer, R. in Morpho-functional Machines: The New Species (eds Hara, F. & Pfeifer, R.) 237–258 (Springer, Tokyo, 2003).

  14. Gruau, F. Genetic synthesis of modular neural networks. In Proc. 5th International Conference on Genetic Algorithms (ed. Forrest, S.) 318–325 (Morgan Kaufmann, San Francisco, 1993).

  15. Khan, M. M., Ahmad, A. M., Khan, G. M. & Miller, J. F. Fast learning neural networks using cartesian genetic programming. Neurocomputing 121, 274–289 (2013).

    Article  Google Scholar 

  16. Turner, A. J. & Miller, J. F. Neuroevolution: evolving heterogeneous artificial neural networks. Evol. Intell. 7, 135–154 (2014).

    Article  Google Scholar 

  17. Mattiussi, C. & Floreano, D. Analog genetic encoding for the evolution of circuits and networks. IEEE Trans. Evol. Comput. 11, 596–607 (2006).

    Article  Google Scholar 

  18. Stanley, K. O. & Miikkulainen, R. Evolving neural networks through augmenting topologies. Evol. Comput. 10, 99–127 (2002).

    Article  Google Scholar 

  19. Moriarty, D. E. & Miikkulainen, R. Evolving obstacle avoidance behavior in a robot arm. In From Animals to Animats 4: Proc. 4th International Conference on Simulation of Adaptive Behavior (eds Maes, P. et al.) 468–475 (MIT Press, Cambridge, 1996).

  20. Nolfi, S. & Floreano, D. Evolutionary Robotics (MIT Press, Cambridge, 2000).

    Google Scholar 

  21. Hornby, G et al. Evolving robust gaits with AIBO. In Proc. IEEE Conference on Robotics and Automation 3040–3045 (IEEE, 2000).

  22. Lipson, H. & Pollack, J. B. Automatic design and manufacture of robotic lifeforms. Nature 406, 974–978 (2000).

    Article  Google Scholar 

  23. Aaltonen, T. et al. Measurement of the top quark mass with dilepton events selected using neuroevolution at CDF. Phys. Rev. Lett. 102, 2001 (2009).

    Google Scholar 

  24. Togelius, J., Yannakakis, G. N., Stanley, K. O. & Browne, C. Search-based procedural content generation: a taxonomy and survey. IEEE Trans. Comput. Intell. AI Games 3, 172–186 (2011).

    Article  Google Scholar 

  25. Stanley, K. O., Bryant, B. D. & Miikkulainen, R. Real-time neuroevolution in the NERO video game. IEEE Trans. Evol. Comput. 9, 653–668 (2005).

    Article  Google Scholar 

  26. Clune, J., Mouret, J.-B. & Lipson, H. The evolutionary origins of modularity. Proc. R. Soc. B 280, 20122863 (2013).

    Article  Google Scholar 

  27. Huizinga, J., Mouret, J.-B. & Clune, J. Evolving neural networks that are both modular and regular: Hyperneat plus the connection cost technique. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 697–704 (ACM, 2014).

  28. Polyak, B. T. Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 4, 1–17 (1964).

    Article  Google Scholar 

  29. Qian, N. On the momentum term in gradient descent learning algorithms. Neural Netw. 12, 145–151 (1999).

    Article  Google Scholar 

  30. LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998).

    Article  Google Scholar 

  31. Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735–1780 (1997).

    Article  Google Scholar 

  32. Dahl, G., Yu, D., Deng, L. & Acero, A. Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20, 30–42 (2012).

  33. Hinton, G. et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29, 82–97 (2012).

    Article  Google Scholar 

  34. Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25 (NIPS 2012) (eds. Pereira, F. et al.) 1097–1105 (NIPS, 2012).

  35. Lillicrap, T. P. et al. Continuous control with deep reinforcement learning. Preprint at (2016).

  36. Schulman, J., Levine, S., Abbeel, P., Jordan, M. & Moritz, P. Trust region policy optimization. J. Mach. Learn. Res. 37, 1889–1897 (2015).

  37. Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O. Proximal policy optimization algorithms. Preprint at (2017).

  38. Salimans, T., Ho, J., Chen, X. & Sutskever, I. Evolution strategies as a scalable alternative to reinforcement learning. Preprint at (2017).

  39. Rechenberg, I. in Simulationsmethoden in der Medizin und Biologie 83–114 (Springer, Hannover, 1978).

  40. Wierstra, D. et al. Natural evolution strategies. J. Mach. Learn. Res. 15, 949–980 (2014).

    MathSciNet  MATH  Google Scholar 

  41. Mnih, V. et al. Asynchronous methods for deep reinforcement learning. In International Conference on Machine Learning 1928–1937 (PMLR, 2016).

  42. Such, F. P. et al. Deep neuroevolution: genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. Preprint at (2017).

  43. Hessel, M. et al. Rainbow: combining improvements in deep reinforcement learning. In Proc. 2018 AAAI Conference on Artificial Intelligence (AAAI, 2017).

  44. Horgan, D. et al. Distributed prioritized experience replay. In Proc. 2018 International Conference on Learning Representations (OpenReview, 2018).

  45. Mania, H., Guy, A. & Recht, B. Simple random search provides a competitive approach to reinforcement learning. Preprint at (2018).

  46. Clune, J., Stanley, K. O., Pennock, R. T. & Ofria, C. On the performance of indirect encoding across the continuum of regularity. IEEE Trans. Evol. Comput. 15, 346–367 (2011).

  47. Cully, A., Clune, J., Tarapore, D. & Mouret, J.-B. Robots that can adapt like animals. Nature 521, 503–507 (2015).

    Article  Google Scholar 

  48. Lehman, J., Chen, J., Clune, J. & Stanley, K. O. Safe mutations for deep and recurrent neural networks through output gradients. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 117–124 (ACM, 2018).

  49. Gangwani, T. & Peng, J. Genetic policy optimization. In Proc. 2018 International Conference on Learning Representations (OpenReview, 2018).

  50. Fortunato, M. et al. Noisy networks for exploration. In Proc. 2018 International Conference on Learning Representations (OpenReview, 2018).

  51. Plappert, M. et al. Parameter space noise for exploration. In Proc. 2018 International Conference on Learning Representations (OpenReview, 2018).

  52. Lehman, J. et al. The surprising creativity of digital evolution: A collection of anecdotes from the evolutionary computation and artificial life research communities. Preprint at (2018).

  53. Conti, E. et al. Improving exploration in evolutionary strategies for deep reinforcement learning via a population of novelty-seeking agents. Advances in Neural Information Processing Systems (NIPS) (Curran Associates, Red Hook, 2018).

  54. Stanton, C. & Clune, J. Deep curiosity search: Intra-life exploration improves performance on challenging deep reinforcement learning problems. Preprint at (2018).

  55. Stanley, K. O. & Miikkulainen, R. A taxonomy for artificial embryogeny. Artif. Life 9, 93–130 (2003).

    Article  Google Scholar 

  56. Rawal, A. & Miikkulainen, R. From nodes to networks: evolving recurrent neural networks. Preprint at (2018).

  57. Real, E., Aggarwal, A., Huang, Y. & Le, Q. V. Regularized evolution for image classifier architecture search. Preprint at (2018).

  58. Dawkins, R. The Extended Phenotype: The Gene as the Unit of Selection (Freeman, Oxford, 1982).

  59. Gould, S. J. Full House (Harvard Univ. Press, Cambridge, 2011).

  60. Goldberg, D. E. & Richardson, J. Genetic algorithms with sharing for multimodal function optimization. In Proc. 2nd International Conference on Genetic Algorithms 41–49 (L. Erlbaum, Hillsdale, 1987).

  61. Mahfoud, S. W. Niching Methods for Genetic Algorithms. PhD thesis, Univ. Illinois at Urbana-Champaign (1995).

  62. Jong, De, K. A. An Analysis of the Behavior of a Class of Genetic Adaptive Systems. PhD thesis, Univ. Michigan (1975).

  63. Lehman, J. & Stanley, K. O. Abandoning objectives: evolution through the search for novelty alone. Evol. Comput. 19, 189–223 (2011).

    Article  Google Scholar 

  64. Neyshabur, B., Salakhutdinov, R. R. & Srebro, N. Path-SGD: path-normalized optimization in deep neural networks. In Advances in Neural Information Processing Systems 28 (NIPS 2015) 2422–2430 (MIT Press, Cambridge, 2015).

  65. Radcliffe, N. J. Genetic set recombination and its application to neural network topology optimisation. Neural Comput. Appl. 1, 67–90 (1993).

    Article  Google Scholar 

  66. Benson-Amram, S. & Holekamp, K. E. Innovative problem solving by wild spotted hyenas. Proc. R. Soc. B 279, 4087–4095 (2012).

    Article  Google Scholar 

  67. Kanter, R. M. The Change Masters: Binnovation and Entrepreneturship in the American Corporation (Simon & Schuster, New York, 1984).

  68. Mouret, J.-B. & Doncieux, S. Encouraging behavioral diversity in evolutionary robotics: an empirical study. Evol. Comput. 20, 91–133 (2012).

    Article  Google Scholar 

  69. Mengistu, H., Lehman, J. & Clune, J. Evolvability search: directly selecting for evolvability in order to study and produce it. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 141–148 (ACM, 2016).

  70. Gravina, D., Liapis, A. & Yannakakis, G. Surprise search: beyond objectives and novelty. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 677–684 (ACM, 2016).

  71. Deb, K., Pratap, A., Agarwal, S. & Meyarivan, T. A. M. T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evolut. Comput. 6, 182–197 (2002).

    Article  Google Scholar 

  72. Zitzler, E. & Thiele, L. Multiobjective evolutionary algorithms: a comparative case study and the strength pareto approach. IEEE Trans. Evolut. Comput. 3, 257–271 (1999).

    Article  Google Scholar 

  73. Pugh, J. K., Soros, L. B. & Stanley, K. O. Quality diversity: a new frontier for evolutionary computation. Front. Robot. AI 3, 40 (2016).

    Article  Google Scholar 

  74. Lehman, J. & Stanley, K. O. Evolving a diversity of virtual creatures through novelty search and local competition. In Proc. 13th Annual Conference on Genetic and Evolutionary Computation (GECCO) 211–218 (ACM, 2011).

  75. Mouret, J.-B. & Clune, J. Illuminating search spaces by mapping elites. Preprint at (2015).

  76. Brant, J. C. & Stanley, K. O. Minimal criterion coevolution: a new approach to open-ended search. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 67–74 (ACM, 2017).

  77. Hodjat, B., Shahrzad, H. & Miikkulainen, R. Distributed age-layered novelty search. In Proc. 15th International Conference on the Synthesis and Simulation of Living Systems (Alife XV) 131–138 (MIT Press, Cambridge, 2016).

  78. Huizinga, J., Mouret, J.-B. & Clune, J. Does aligning phenotypic and genotypic modularity improve the evolution of neural networks? In Proc. Genetic and Evolutionary Computation Conference (GECCO) 125–132 (ACM, 2016).

  79. Meyerson, E. & Miikkulainen, R. Discovering evolutionary stepping stones through behavior domination. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 139–146 (ACM, 2017).

  80. Nguyen, A., Yosinski, J. & Clune, J. Understanding innovation engines: automated creativity and improved stochastic optimization via deep learning. Evol. Comput. 24, 545–572 (2016).

    Article  Google Scholar 

  81. Herculano-Houzel, S. The human brain in numbers: a linearly scaled-up primate brain. Front. Hum. Neurosci. 3, 31 (2009).

    Article  Google Scholar 

  82. Venter, J. C. et al. The sequence of the human genome. Science 291, 1304–1351 (2001).

    Article  Google Scholar 

  83. Striedter, G. F. Principles of Brain Evolution (Sinauer Associates, Sunderland, 2005).

    Google Scholar 

  84. Russakovsky, O. et al. Imagenet large scale visual recognition challenge. Int. J. Comput. Vision. 115, 211–252 (2015).

    Article  MathSciNet  Google Scholar 

  85. Turing, A. The chemical basis of morphogenesis. Phil. Trans. R. Soc. B 237, 37–72 (1952).

    Article  MathSciNet  Google Scholar 

  86. Lindenmayer, A. Mathematical models for cellular interactions in development I. Filaments with one-sided inputs. J. Theor. Biol. 18, 280–299 (1968).

    Article  Google Scholar 

  87. Bongard, J. C. & Pfeifer, R . Repeated structure and dissociation of genotypic and phenotypic complexity in artificial ontogeny. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 829–836 (Kaufmann, 2001).

  88. Hornby, G. S. & Pollack, J. B. Creating high-level components with a generative representation for body-brain evolution. Artif. Life 8, 223–246 (2002).

    Article  Google Scholar 

  89. Stanley, K. O. Compositional pattern producing networks: a novel abstraction of development. Genet. Program. Evol. Mach. Spec. Issue Dev. Syst. 8, 131–162 (2007).

    Article  Google Scholar 

  90. Meinhardt, H. Models of Biological Pattern Formation (Academic, London, 1982).

  91. Secretan, J. et al. Picbreeder: a case study in collaborative evolutionary exploration of design space. Evol. Comput. 19, 345–371 (2011).

    Article  Google Scholar 

  92. Clune, J. & Lipson, H. Evolving three-dimensional objects with a generative encoding inspired by developmental biology. In Proc. European Conference on Artificial Life 144–148 (MIT Press, Cambridge, 2011).

  93. Cheney, N, MacCurdy, R, Clune, J. & Lipson, H. Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding. In Proc. Genetic and Evolutionary Computation Conference (GECCO) (ACM, 2013).

  94. Nguyen, A., Yosinski, J. & Clune, J. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2015).

  95. Huizinga, J., Stanley, K. O. & Clune, J. The emergence of canalization and evolvability in an open-ended, interactive evolutionary system. Artif. Life 24, 157–181 (2018).

    Article  Google Scholar 

  96. Liu, R. et al. An intriguing failing of convolutional neural networks and the coordconv solution. In Proc. 2018 Conference on Neural Information Processing Systems (NIPS) (Curran Associates, Red Hook, 2018).

  97. Gauci, J. & Stanley, K. O. Autonomous evolution of topographic regularities in artificial neural networks. Neural Comput. 22, 1860–1898 (2010).

    Article  Google Scholar 

  98. Stanley, K. O., D’Ambrosio, D. B. & Gauci, J. A hypercube-based indirect encoding for evolving large-scale neural networks. Artif. Life 15, 185–212 (2009).

    Article  Google Scholar 

  99. Fernando, C. et al. Convolution by evolution: differentiable pattern producing networks. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 109–116 (ACM, 2016).

  100. Ha, D., Dai, A. & Le, Q. V. Hypernetworks. In Proc. 2017 International Conference on Learning Representations Vol. 2 (OpenReview, 2017).

  101. van Steenkiste, S., Koutník, J., Driessens, K. & Schmidhuber, J. A wavelet-based encoding for neuroevolution. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 517–524 (ACM, 2016).

  102. Koutnik, J., Gomez, F. & Schmidhuber, J. Evolving neural networks in compressed weight space. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 619–626 (ACM, 2010).

  103. Hausknecht, M., Lehman, J., Miikkulainen, R. & Stone, P. A neuroevolution approach to general atari game playing. IEEE Trans. Comput. Intell. AI Games 6, 355–366 (2014).

    Article  Google Scholar 

  104. Turner, A. J. & Miller, J. F. Recurrent cartesian genetic programming of artificial neural networks. Genet. Program. Evol. Mach. 18, 185–212 (2017).

    Article  Google Scholar 

  105. Risi, S. & Stanley, K. O. Indirectly encoding neural plasticity as a pattern of local rules. In Proc 11th International Conference on Simulation of Adaptive Behavior (Springer, New York, 2010).

  106. Risi, S. & Stanley, K. O. An enhanced hypercube-based encoding for evolving the placement, densty and connectivity of neurons. Artif. Life J. 18, 331–363 (2012).

    Article  Google Scholar 

  107. Schmidhuber, J. Evolutionary Principles in Self-referential Learning, or on Learning How to Learn: The Meta-meta-...Hook. PhD thesis, Technische Univ. München (1987).

  108. Duan, Y. et al. RL2: Fast reinforcement learning via slow reinforcement learning. Preprint at (2016).

  109. Finn, C, Abbeel, P. & Levine, S. Model-agnostic meta-learning for fast adaptation of deep networks. In Proc. 34th International Conference on Machine Learning 1126–1135 (PMLR, 2017).

  110. Miconi, T. Learning to learn with backpropagation of Hebbian plasticity. Preprint at (2016).

  111. Wang, J. X. et al. Learning to reinforcement learn. Preprint at (2016).

  112. Floreano, D. & Urzelai, J. Evolutionary robots with on-line self-organization and behavioral fitness. Neural Netw. 13, 431–4434 (2000).

    Article  Google Scholar 

  113. Floreano, D. & Mondada, F. Evolution of plastic neurocontrollers for situated agents. IEEE Trans. Syst. Man. Cybern. 26, 396–407 (1996).

    Article  Google Scholar 

  114. Hebb, D. O. The Organization of Behavior: A Neuropsychological Theory (Wiley, Hoboken, 1949).

  115. Soltoggio, A., Bullinaria, A. J., Mattiussi, C., Dürr, P. & Floreano, D. Evolutionary advantages of neuromodulated plasticity in dynamic, reward-based scenarios. In Proc. 11th International Conference on Artificial Life (Alife XI) (eds Bullock, S. et al.) 569–576 (MIT Press, Cambridge, 2008).

  116. Risi, S. & Stanley, K. O. A unified approach to evolving plasticity and neural geometry. In Proc. International Joint Conference on Neural Networks (IJCNN-2012) (IEEE, 2012).

  117. Tonelli, P. & Mouret, J.-B. On the relationships between generative encodings, regularity, and learning abilities when evolving plastic artificial neural networks. PLoS One 8, e79138 (2013).

    Article  Google Scholar 

  118. Barnes, J. M. & Underwood, B. J. ‘Fate’ of first-list associations in transfer theory. J. Exp. Psychol. 58, 97 (1959).

    Article  Google Scholar 

  119. French, R. M. Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3, 128–135 (1999).

    Article  Google Scholar 

  120. Ellefsen, K. O., Mouret, J.-B., Clune, J. & Bongard, J. C. Neural modularity helps organisms evolve to learn new skills without forgetting old skills. PLoS Comput. Biol. 11, e1004128 (2015).

    Article  Google Scholar 

  121. Velez, R. & Clune, J. Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks. PLoS One 12, e0187736 (2017).

    Article  Google Scholar 

  122. Kirkpatrick, J. et al. Overcoming catastrophic forgetting in neural networks. Proc. Natl Acad. Sci. USA 114, 3521–3526 (2017).

  123. Zenke, F, Poole, B. & Ganguli, S. Continual learning through synaptic intelligence. In Proc. 34th International Conference on Machine Learning 3987–3995 (PMLR, 2017).

  124. Miikkulainen, R. et al. Evolving deep neural networks. Preprint at (2017).

  125. He, K., Zhang, X., Ren, S. & Sun, J. Identity mappings in deep residual networks. In European Conference on Computer Vision 630–645 (Springer, Berlin, 2016).

  126. G. Huang,Liu, Z. Van Der Maaten, L. &Weinberger, K. Q. Densely connected convolutional networks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2017).

  127. Szegedy, C., Ioffe, S. & Vanhoucke, V. Inception-v4, Inception-ResNet and the impact of residual connections on learning. In Proc. 2017 AAAI Conference on Artificial Intelligence 4278–4284 (AAAI, 2017).

  128. Real, E. et al. Large-scale evolution of image classifiers. In Proc. 34th International Conference on Machine Learning (eds Precup, D. & Teh, Y. W.) 2902–2911 (PLMR, 2017).

  129. Zoph, B., Vasudevan, V., Shlens, J. & Le, Q. V. Learning transferable architectures for scalable image recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 8697–8710 (IEEE, 2018).

  130. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 770–778 (IEEE, 2016).

  131. Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V. & Le, Q. V. Autoaugment: learning augmentation policies from data. Preprint at (2018).

  132. Schmidhuber, J. Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015).

    Article  Google Scholar 

  133. Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R. & Schmidhuber, J. LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28, 2222–2232 (2017).

    Article  MathSciNet  Google Scholar 

  134. Melis, G., Dyer, C. & Blunsom, P. On the state of the art of evaluation in neural language models. In Proc. 2018 International Conference on Learning Representations (OpenReview, 2018).

  135. Zoph, B. & Le, Q. V. Neural architecture search with reinforcement learning. In Proc. 2017 International Conference on Learning Representations (OpenReview, 2017).

  136. Marcus, M. P., Santorini, B. & Marcinkiewicz, M. A. Building a large annotated corpus of English: the Penn treebank. Comput. Linguist. 19, 313–330 (1993).

    Google Scholar 

  137. Caruana, R. Multitask learning. Mach. Learn. 28, 41–75 (1997).

    Article  Google Scholar 

  138. Meyerson, E. & Miikkulainen, R. Pseudo-task augmentation: from deep multitask learning to intratask sharing—and back. In Proc. 35th International Conference on Machine Learning (PMLR, 2018).

  139. Liang, J., Meyerson, E. & Miikkulainen, R. Evolutionary architecture search for deep multitask networks. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 466–473 (ACM, 2018).

  140. Elsken, T., Metzen, J. H. & Hutter, F. Neural architecture search: a survey. Preprint at (2017).

  141. Fernando, C. et al. Pathnet: evolution channels gradient descent in super neural networks. Preprint at (2017).

  142. Houthooft, R. et al. Evolved policy gradients. Preprint at (2018).

  143. Wang, C., Xu, C., Yao, X. & Tao, D. Evolutionary generative adversarial networks. Preprint at (2018).

  144. Jaderberg, M. et al. Population based training of neural networks. Preprint at (2017).

  145. Jaderberg, M. et al. Human-level performance in first-person multiplayer games with population-based deep reinforcement learning. Preprint at (2018).

  146. Eysenbach, B., Gupta, A., Ibarz, J. & Levine, S. Diversity is all you need: learning skills without a reward function. Preprint at (2018).

  147. Miconi, T., Clune, J. & Stanley, K. O. Differentiable plasticity: training plastic neural networks with backpropagation. Proc. International Conference on Machine Learning 3556–3565 (PMLR, 2018).

  148. Mordvintsev, A., Pezzotti, N., Schubert, L. & Olah, C. Differentiable image parameterizations. Distill 3, e12 (2018).

    Article  Google Scholar 

  149. Bansal, T., Pachocki, J., Sidor, S., Sutskever, I. & Mordatch, I. Emergent complexity via multi-agent competition. In Proc. 2018 International Conference on Learning Representations (OpenReview, 2018).

  150. Silver, D. et al. Mastering the game of Go without human knowledge. Nature 550, 354–359 (2017).

    Article  Google Scholar 

  151. Paredis, J. Coevolutionary computation. Artif. Life 2, 355–375 (1995).

    Article  Google Scholar 

  152. Pollack, J. B., Blair, A. D. & Land, M. Coevolution of a backgammon player. In Proc. 5th International Workshop on Artificial Life: Synthesis and Simulation of Living Systems (ALIFE-96) (eds Langton. C. G. & Shimohara, K.) (MIT Press, Cambridge, 1996).

  153. Potter, M. A. & De Jong, K. A. Evolving neural networks with collaborative species. In Proc. 1995 Summer Computer Simulation Conference 340–345 (Society for Computer Simulation, 1995).

  154. Rosin, C. D. & Belew, R. K. Methods for competitive co-evolution: finding opponents worth beating. In Proc. 1995 International Conference on Genetic Algorithms 373–381 (Morgan Kaufmann, Burlington, 1995).

  155. Cussat-Blanc, S., Harrington, K. & Pollack, J. Gene regulatory network evolution through augmenting topologies. IEEE Trans. Evolut. Comput. 19, 823–837 (2015).

    Article  Google Scholar 

  156. Auerbach, J. E. & Bongard, J. C.On the relationship between environmental and morphological complexity in evolved robots. In Proc. Genetic and Evolutionary Computation Conference (GECCO) 521–528 (ACM, 2012).

  157. Pfeifer, R. & Bongard, J. How the Body Shapes the Way We Think: A New View of Intelligence (MIT Press, Cambridge, 2006).

  158. Howard, D. et al. Evolving embodied intelligence from materials to machines. Nat. Mach. Intell. (2019).

  159. Stanley, K. O., Lehman, J. & Soros, L. Open-endedness: the last grand challenge you’ve never heard of. O’Reilly Online (2017).

Download references

Author information

Authors and Affiliations


Corresponding authors

Correspondence to Kenneth O. Stanley, Jeff Clune, Joel Lehman or Risto Miikkulainen.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note: Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Stanley, K.O., Clune, J., Lehman, J. et al. Designing neural networks through neuroevolution. Nat Mach Intell 1, 24–35 (2019).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:

This article is cited by


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing