Close menu

SURE

Sunderland Repository records the research produced by the University of Sunderland including practice-based research and theses.

Homeostatic Fault Tolerance in Spiking Neural Networks: A Dynamic Hardware Perspective

Johnson, Anju P, Junxiu, Liu, Millard, Alan G, Shvan, Karim, Tyrrel, Andy M, Harkin, Jim, Timmis, Jonathan, McDaid, Liam J and Halliday, David M (2017) Homeostatic Fault Tolerance in Spiking Neural Networks: A Dynamic Hardware Perspective. IEEE Transactions on Circuits and Systems, 65 (2). pp. 687-689. ISSN 1549-8328

Item Type: Article

Abstract

Fault tolerance is a remarkable feature of biological systems and their self-repair capability influence modern electronic systems. In this paper, we propose a novel plastic neural network model, which establishes homeostasis in a spiking neural network. Combined with this plasticity and the inspiration from inhibitory interneurons, we develop a fault-resilient robotic controller implemented on an FPGA establishing obstacle avoidance task. We demonstrate the proposed methodology on a spiking neural network implemented on Xilinx Artix-7 FPGA. The system is able to maintain stable firing (tolerance ±10%) with a loss of up to 75% of the original synaptic inputs to a neuron. Our repair mechanism has minimal hardware overhead with a tuning circuit (repair unit) which consumes only three slices/neuron for implementing a threshold voltage-based homeostatic fault-tolerant unit. The overall architecture has a minimal impact on power consumption and, therefore, supports scalable implementations. This paper opens a novel way of implementing the behavior of natural fault tolerant system in hardware establishing homeostatic self-repair behavior.

Full text not available from this repository.

More Information

Depositing User: Klaire Purvis-Shepherd

Identifiers

Item ID: 10849
Identification Number: https://doi.org/10.1109/TCSI.2017.2726763
ISSN: 1549-8328
URI: http://sure.sunderland.ac.uk/id/eprint/10849
Official URL: https://ieeexplore.ieee.org/document/7995041

Users with ORCIDS

Catalogue record

Date Deposited: 07 Jun 2019 13:55
Last Modified: 07 Jun 2019 14:52

Contributors

Author: Anju P Johnson
Author: Liu Junxiu
Author: Alan G Millard
Author: Karim Shvan
Author: Andy M Tyrrel
Author: Jim Harkin
Author: Jonathan Timmis
Author: Liam J McDaid
Author: David M Halliday

University Divisions

Services > University Executive

Subjects

Sciences > Biomedical Sciences
Computing

Actions (login required)

View Item View Item