How generative encodings fare on less regular problems

ABSTRACT

Generative representations allow the reuse of code and thus facilitate the evolution of repeated phenotypic themes or modules. It has been shown that generative representations perform well on highly regular problems. To date, however, generative representations have not been tested on irregular problems. It is unknown how fast their performance degrades as the regularity of the problem decreases. In this report, we test a generative representation on a problem where we can scale a type of regularity in the problem. The generative representation outperforms a direct encoding control when the regularity of the problem is high but degrades to, and then underperforms, the direct control as the regularity of the problem decreases. Importantly, this decrease is not linear. The boost provided by the generative encoding is only significant for very high levels of regularity.

REFERENCES

• 1: Kenneth O. Stanley , Risto Miikkulainen, A Taxonomy for artificial embryogeny, Artificial Life, v.9 n.2, p.93-130, Spring 2003 [doi>10.1162/106454603322221487]
• 2: David B. D'Ambrosio , Kenneth O. Stanley, A novel generative encoding for exploiting neural network sensor and output geometry, Proceedings of the 9th annual conference on Genetic and evolutionary computation, July 07-11, 2007, London, England [doi>10.1145/1276958.1277155]
• 3: Jason Gauci , Kenneth Stanley, Generating large-scale neural networks through discovering geometric regularities, Proceedings of the 9th annual conference on Genetic and evolutionary computation, July 07-11, 2007, London, England [doi>10.1145/1276958.1277158]
• 4: Kenneth O. Stanley , Risto Miikkulainen, Evolving neural networks through augmenting topologies, Evolutionary Computation, v.10 n.2, p.99-127, Summer 2002 [doi>10.1162/106365602320169811]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Connectionism and neural nets

General Terms:
Algorithms, Experimentation

Keywords:
ANN, HyperNEAT, NEAT, evolution, modularity, regularity