Building artificial CPGs with asymmetric Hopfield networks

Conference paper


Franca, F. and Yang, Z. 2000. Building artificial CPGs with asymmetric Hopfield networks. The IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN 2000). Como, Italy 24 - 27 Jul 2000
TypeConference paper
TitleBuilding artificial CPGs with asymmetric Hopfield networks
AuthorsFranca, F. and Yang, Z.
Abstract

This paper presents a novel approach to the emulation of locomotor central pattern generators (CPGs) of legged animals. Based on Scheduling by Multiple Edge Reversal (SMER), a simple but powerful distributed algorithm, it is shown how oscillatory building blocks (OBBs) can be created and how OBB-based networks can be implemented as asymmetric Hopfield-like neural networks for the generation of complicatedly coordinated rhythmic patterns observed among pairs of biological motor neurons working during different gait patterns. It is also presented how a generalized CPG model mapped into such Hopfield-like networks possess some charming properties on the retrieval of a whole range of different preprogrammed gait patterns.

ConferenceThe IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN 2000)
Publication dates
Print2000
Publication process dates
Deposited05 Feb 2013
Output statusPublished
Web address (URL)http://dx.doi.org/10.1109/IJCNN.2000.860787
LanguageEnglish
Permalink -

https://repository.mdx.ac.uk/item/83y0x

  • 23
    total views
  • 0
    total downloads
  • 0
    views this month
  • 0
    downloads this month

Export as