Evolving Neural Networks That Are Both Modular and Regular: HyperNeat Plus the Connection Cost Technique - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

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

Résumé

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.
Fichier principal
Vignette du fichier
2014ACTI3120.pdf (907.64 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01300699 , version 1 (11-04-2016)

Identifiants

  • HAL Id : hal-01300699 , version 1

Citer

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⟩
134 Consultations
732 Téléchargements

Partager

Gmail Facebook X LinkedIn More