Ulster University Logo

A new biologically plausible supervised learning method for spiking neurons

Taherkhani, Aboozar, Belatreche, Ammar, Li, Yuhua and Maguire, Liam (2014) A new biologically plausible supervised learning method for spiking neurons. In: 22st European Symposium on Artificial Neural Networks, Computational Intelligence And Machine Learning, Bruges, Belgium. i6doc.com publ.. 6 pp. [Conference contribution]

Full text not available from this repository.

URL: http://www.i6doc.com/fr/livre/?GCOI=28001100432440

Abstract

STDP is believed to play an important role in learning and memory. Additionally, experimental evidence shows that a few strong neural inputs can drive a neuron response and subsequently affect the learning of other inputs. Furthermore, recent studies have shown that local dendritic depolarization canimpact STDP induction. This paper integrates these three biological concepts to devise a new biologically plausible supervised learning method for spiking neurons. Experimental results show that the proposed method can effectively map a random spatiotemporal input pattern to a random target output spike train with a much faster learning speed than ReSuMe.

Item Type:Conference contribution (Paper)
Faculties and Schools:Faculty of Computing & Engineering
Faculty of Computing & Engineering > School of Computing and Intelligent Systems
Research Institutes and Groups:Computer Science Research Institute > Intelligent Systems Research Centre
Computer Science Research Institute
ID Code:30304
Deposited By: Dr Ammar Belatreche
Deposited On:01 Oct 2014 10:09
Last Modified:01 Oct 2014 10:09

Repository Staff Only: item control page