Automatic definition of modular neural networks
Adaptive Behavior
Evolving neural networks through augmenting topologies
Evolutionary Computation
Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines
Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines
Compositional pattern producing networks: A novel abstraction of development
Genetic Programming and Evolvable Machines
Modular neuroevolution for multilegged locomotion
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Generative encoding for multiagent learning
Proceedings of the 10th annual conference on Genetic and evolutionary computation
A case study on the critical role of geometric regularity in machine learning
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
Evolving 3d morphology and behavior by competition
Artificial Life
Evolving coordinated quadruped gaits with the HyperNEAT generative encoding
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Autonomous evolution of dynamic gaits with two quadruped robots
IEEE Transactions on Robotics
IEEE Transactions on Neural Networks
Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers
Generative and developmental systems
Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers
Neuroevolution of mobile ad hoc networks
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Evolving CPPNs to grow three-dimensional physical structures
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Investigating whether hyperNEAT produces modular neural networks
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Generative and developmental systems
Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Evolving policy geometry for scalable multiagent learning
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Evolving complete robots with CPPN-NEAT: the utility of recurrent connections
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Proceedings of the 13th annual conference companion on Genetic and evolutionary computation
HybrID: a hybridization of indirect and direct encodings for evolutionary computation
ECAL'09 Proceedings of the 10th European conference on Advances in artificial life: Darwin meets von Neumann - Volume Part II
On the relationship between environmental and morphological complexity in evolved robots
Proceedings of the 14th annual conference on Genetic and evolutionary computation
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
Generative and developmental systems
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation
Critical factors in the performance of hyperNEAT
Proceedings of the 15th annual conference on Genetic and evolutionary computation
Generative and developmental systems
Proceedings of the 15th annual conference companion on Genetic and evolutionary computation
Hi-index | 0.00 |
HyperNEAT, a generative encoding for evolving artificial neural networks (ANNs), has the unique and powerful ability to exploit the geometry of a problem (e.g., symmetries) by encoding ANNs as a function of a problem's geometry. This paper provides the first extensive analysis of the sensitivity of HyperNEAT to different geometric representations of a problem. Understanding how geometric representations affect the quality of evolved solutions should improve future designs of such representations. HyperNEAT has been shown to produce coordinated gaits for a simulated quadruped robot with a specific two-dimensional geometric representation. Here, the same problem domain is tested, but with different geometric representations of the problem. Overall, experiments show that the quality and kind of solutions produced by HyperNEAT can be substantially affected by the geometric representation. HyperNEAT outperforms a direct encoding control even with randomized geometric representations, but performs even better when a human engineer designs a representation that reflects the actual geometry of the robot. Unfortunately, even choices in geometric layout that seem to be inconsequential a priori can significantly affect fitness. Additionally, a geometric representation can bias the type of solutions generated (e.g., make left-right symmetry more common than front-back symmetry). The results suggest that HyperNEAT practitioners can obtain good results even if they do not know how to geometrically represent a problem, and that further improvements are possible with a well-chosen geometric representation.