A Taxonomy for artificial embryogeny
Artificial Life
Measuring, enabling and comparing modularity, regularity and hierarchy in evolutionary design
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Self modifying cartesian genetic programming: parity
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
A Field Guide to Genetic Programming
A Field Guide to Genetic Programming
Investigating whether hyperNEAT produces modular neural networks
Proceedings of the 12th annual conference on Genetic and evolutionary computation
On the Performance of Indirect Encoding Across the Continuum of Regularity
IEEE Transactions on Evolutionary Computation
Critical factors in the performance of hyperNEAT
Proceedings of the 15th annual conference on Genetic and evolutionary computation
Graph grammars for evolutionary 3D design
Genetic Programming and Evolvable Machines
Hi-index | 0.00 |
In this paper we introduce the Developmental Symbolic Encoding (DSE), a new generative encoding for evolving networks (e.g. neural or boolean). DSE combines elements of two powerful generative encodings, Cellular Encoding and HyperNEAT, in order to evolve networks that are modular, regular, scale-free, and scalable. Generating networks with these properties is important because they can enhance performance and evolvability. We test DSE's ability to generate scale-free and modular networks by explicitly rewarding these properties and seeing whether evolution can produce networks that possess them. We compare the networks DSE evolves to those of HyperNEAT. The results show that both encodings can produce scale-free networks, although DSE performs slightly, but significantly, better on this objective. DSE networks are far more modular than HyperNEAT networks. Both encodings produce regular networks. We further demonstrate that individual DSE genomes during development can scale up a network pattern to accommodate different numbers of inputs. We also compare DSE to HyperNEAT on a pattern recognition problem. DSE significantly outperforms HyperNEAT, suggesting that its potential lay not just in the properties of the networks it produces, but also because it can compete with leading encodings at solving challenging problems. These preliminary results imply that DSE is an interesting new encoding worthy of additional study. The results also raise questions about which network properties are more likely to be produced by different types of generative encodings.