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.

[img] PDF
davies.2013.pdf - Published Version
Restricted to Repository staff only
All rights reserved.

Download (3MB)
Official URL: https://ieeexplore.ieee.org/document/6706962
Link to published version:: https://doi.org/10.1109/ijcnn.2013.6706962


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 View Item


Downloads per month over past year

View more statistics