The Case for a Mixed-Initiative Collaborative Neuroevolution Approach

08/05/2014 ∙ by Sebastian Risi, et al. ∙ 0

It is clear that the current attempts at using algorithms to create artificial neural networks have had mixed success at best when it comes to creating large networks and/or complex behavior. This should not be unexpected, as creating an artificial brain is essentially a design problem. Human design ingenuity still surpasses computational design for most tasks in most domains, including architecture, game design, and authoring literary fiction. This leads us to ask which the best way is to combine human and machine design capacities when it comes to designing artificial brains. Both of them have their strengths and weaknesses; for example, humans are much too slow to manually specify thousands of neurons, let alone the billions of neurons that go into a human brain, but on the other hand they can rely on a vast repository of common-sense understanding and design heuristics that can help them perform a much better guided search in design space than an algorithm. Therefore, in this paper we argue for a mixed-initiative approach for collaborative online brain building and present first results towards this goal.



There are no comments yet.


page 2

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.


  • Bongard and Hornby (2013) Bongard, J. C. and Hornby, G. S. (2013). Combining fitness-based search and user modeling in evolutionary robotics. In Proceeding of the fifteenth annual conference on Genetic and evolutionary computation conference, pages 159–166. ACM.
  • Clune and Lipson (2011) Clune, J. and Lipson, H. (2011). Evolving three-dimensional objects with a generative encoding inspired by developmental biology. In Proceedings of the European Conference on Artificial Life, See http://EndlessForms. com.
  • Clune et al. (2011) Clune, J., Stanley, K. O., Pennock, R. T., and Ofria, C. (2011). On the performance of indirect encoding across the continuum of regularity. Evolutionary Computation, IEEE Transactions on, 15(3):346–367.
  • Floreano et al. (2008) Floreano, D., Dürr, P., and Mattiussi, C. (2008). Neuroevolution: from architectures to learning. Evol. Intelligence, 1(1):47–62.
  • Lehman and Stanley (2011) Lehman, J. and Stanley, K. O. (2011). Abandoning objectives: Evolution through the search for novelty alone. Evolutionary Computation, 19(2):189–223.
  • Liapis et al. (2014) Liapis, A., Shaker, N., and Smith, G. (2014). Mixed-initiative approaches. In Shaker, N., Togelius, J., and Nelson, M. J., editors, Procedural Content Generation in Games: A Textbook and an Overview of Current Research. Springer.
  • Liapis et al. (2013) Liapis, A., Yannakakis, G. N., and Togelius, J. (2013). Sentient sketchbook: Computer-aided game level authoring. In Proceedings of ACM Conference on Foundations of Digital Games (FDG).
  • Risi (2013) Risi, S. (2013). A compiler for cppns: Transforming phenotypic descriptions into genotypic representations. In 2013 AAAI Fall Symposium Series.
  • Risi and Stanley (2012) Risi, S. and Stanley, K. O. (2012). An enhanced hypercube-based encoding for evolving the placement, density, and connectivity of neurons. Artificial Life, 18(4):331–363.
  • Secretan et al. (2011) Secretan, J., Beato, N., D’Ambrosio, D., Rodriguez, A., Campbell, A., Folsom-Kovarik, J., and Stanley, K. (2011). Picbreeder: A case study in collaborative evolutionary exploration of design space. Evolutionary Computation, 19(3):373–403.
  • Stanley (2007) Stanley, K. O. (2007). Compositional pattern producing networks: A novel abstraction of development. Genetic Programming and Evolvable Machines Special Issue on Developmental Systems, 8(2):131–162.
  • Stanley et al. (2009) Stanley, K. O., D’Ambrosio, D. B., and Gauci, J. (2009). A hypercube-based indirect encoding for evolving large-scale neural networks. Artificial Life, 15(2):185–212.
  • Stanley and Miikkulainen (2004) Stanley, K. O. and Miikkulainen, R. (2004). Competitive coevolution through evolutionary complexification. JAIR, 21:63–100.
  • Woolley and Stanley (2011) Woolley, B. G. and Stanley, K. O. (2011). On the deleterious effects of a priori objectives on evolution and representation. In Proceedings of the 13th annual conference on Genetic and evolutionary computation, pages 957–964. ACM.
  • Woolley and Stanley (2014) Woolley, B. G. and Stanley, K. O. (2014). A novel human-computer collaboration: Combining novelty search with interactive evolution. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2014), New York, NY, USA. ACM.
  • Yannakakis et al. (2014) Yannakakis, G. N., Liapis, A., and Alexopoulos, C. (2014). Mixed-initiative co-creativity. In Proceedings of the 9th Conference on the Foundations of Digital Games.
  • Yao (1999) Yao, X. (1999). Evolving artificial neural networks. Proceedings of the IEEE, 87(9).