A new biologically plausible supervised learning method for spiking neurons

Taherkhani, A; Belatreche, A; Li, Y; Maguire, L

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 can impact 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.

Citation

Taherkhani, A., Belatreche, A., Li, Y., & Maguire, L. (2014, April). A new biologically plausible supervised learning method for spiking neurons. Presented at 22st European Symposium on Artificial Neural Networks (ESANN) Computational Intelligence And Machine Learning, Bruges, Belgium

• Presentation Conference Type: Other
• Conference Name: 22st European Symposium on Artificial Neural Networks (ESANN) Computational Intelligence And Machine Learning
• Conference Location: Bruges, Belgium
• Start Date: Apr 23, 2014
• End Date: Apr 25, 2014
• Publication Date: Apr 23, 2014
• Deposit Date: Jun 19, 2015
• Publisher URL: http://www.i6doc.com/fr/livre/?GCOI=28001100432440
• Related Public URLs: https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2014-50.pdf
• Additional Information: Event Type : Conference