Spike-based learning of transfer functions with the SpiNNaker neuromimetic simulator

DAVIES, Sergio, STEWART, Terry, ELIASMITH, Chris and FURBER, Steve (2014). Spike-based learning of transfer functions with the SpiNNaker neuromimetic simulator. In: The 2013 International Joint Conference on Neural Networks (IJCNN). IEEE.

PDF davies.2013.pdf - Published Version Restricted to Repository staff only All rights reserved. Download (3MB)

Abstract

Recent papers have shown the possibility to implement large scale neural network models that perform complex algorithms in a biologically realistic way. However, such models have been simulated on architectures unable to perform real-time simulations. In previous work we presented the possibility to simulate simple models in real-time on the SpiNNaker neuromimetic architecture. However, such models were “static”: the algorithm performed was defined at design-time. In this paper we present a novel learning rule, that exploits the peculiarities of the SpiNNaker system, enabling models designed with the Neural Engineering Framework (NEF) to learn transfer functions using a supervised framework. We show that the proposed learning rule, belonging to the Prescribed Error Sensitivity (PES) class, is able to learn, effectively, both linear and non-linear functions.

Item Type:	Book Section
Additional Information:	E-ISSN: 2161-4407
Identification Number:	https://doi.org/10.1109/ijcnn.2013.6706962
SWORD Depositor:	Symplectic Elements
Depositing User:	Symplectic Elements
Date Deposited:	28 Apr 2020 11:24
Last Modified:	18 Mar 2021 01:52
URI:	https://shura.shu.ac.uk/id/eprint/24472

Actions (login required)

View Item

Downloads

Publication Metrics