Evolving Neural Networks That Are Both Modular and Regular: HyperNeat Plus the Connection Cost Technique

Abstract : One of humanity’s grand scientific challenges is to create artificially intelligent robots that rival natural animals in intelligence and agility. A key enabler of such animal complexity is the fact that animal brains are structurally organized in that they exhibit modularity and regularity, amongst other attributes. Modularity is the localization of function within an encapsulated unit. Regularity refers to the compressibility of the information describing a structure, and typically involves symmetries and repetition. These properties improve evolvability, but they rarely emerge in evolutionary algorithms without specific techniques to encourage them. It has been shown that (1) modularity can be evolved in neural networks by adding a cost for neural connections and, separately, (2) that the HyperNEAT algorithm produces neural networks with complex, functional regularities. In this pa- per we show that adding the connection cost technique to HyperNEAT produces neural networks that are significantly more modular, regular, and higher performing than Hyper- NEAT without a connection cost, even when compared to a variant of HyperNEAT that was specifically designed to en- courage modularity. Our results represent a stepping stone towards the goal of producing artificial neural networks that share key organizational properties with the brains of natu- ral animals.
Document type :
Conference papers
Complete list of metadatas

Cited literature [38 references]  Display  Hide  Download

Contributor : Jean-Baptiste Mouret <>
Submitted on : Monday, April 11, 2016 - 10:31:45 PM
Last modification on : Thursday, March 21, 2019 - 1:21:04 PM
Long-term archiving on : Tuesday, July 12, 2016 - 11:47:13 AM


Files produced by the author(s)


  • HAL Id : hal-01300699, version 1


Joost Huizinga, Jean-Baptiste Mouret, Jeff Clune. Evolving Neural Networks That Are Both Modular and Regular: HyperNeat Plus the Connection Cost Technique. GECCO '14: Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation, ACM, 2014, Vancouver, Canada. pp.697-704. ⟨hal-01300699⟩



Record views


Files downloads