Modular non-computational-connectionist-hybrid neural network approach to robotic systems

Bamford, C. D. and Mitchell, R. J. (2011) Modular non-computational-connectionist-hybrid neural network approach to robotic systems. Paladyn. Journal of Behavioral Robotics, 2 (3). pp. 126-133. ISSN 2081-4836 doi: 10.2478/s13230-012-0003-6 (special issue: Cybernetic Approaches to Robotics)

Abstract/Summary

Spiking neural networks are usually limited in their applications due to their complex mathematical models and the lack of intuitive learning algorithms. In this paper, a simpler, novel neural network derived from a leaky integrate and fire neuron model, the ‘cavalcade’ neuron, is presented. A simulation for the neural network has been developed and two basic learning algorithms implemented within the environment. These algorithms successfully learn some basic temporal and instantaneous problems. Inspiration for neural network structures from these experiments are then taken and applied to process sensor information so as to successfully control a mobile robot.

Item Type	Article
URI	https://reading-clone.eprints-hosting.org/id/eprint/28244
Item Type	Article
Refereed	Yes
Divisions	Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
Uncontrolled Keywords	neural networks – robotics – spiking neurons – hybrid systems
Publisher	Versita; Springer
Download/View statistics	View download statistics for this item