Header

UZH-Logo

Maintenance Infos

Efficient implementation of STDP rules on SpiNNaker neuromorphic hardware


Diehl, P U; Cook, M (2014). Efficient implementation of STDP rules on SpiNNaker neuromorphic hardware. In: The International Joint Conference on Neural Networks (IJCNN), Beijing, China, 6 July 2014 - 11 July 2014, 4288-4295.

Abstract

Recent development of neuromorphic hardware offers great potential to speed up simulations of neural networks. SpiNNaker is a neuromorphic hardware and software system designed to be scalable and flexible enough to implement a variety of different types of simulations of neural systems, including spiking simulations with plasticity and learning. Spike-timing dependent plasticity (STDP) rules are the most common form of learning used in spiking networks. However, to date very few such rules have been implemented on SpiNNaker, in part because implementations must be designed to fit the specialized nature of the hardware. Here we explain how general STDP rules can be efficiently implemented in the SpiNNaker system. We give two examples of applications of the implemented rule: learning of a temporal sequence, and balancing inhibition and excitation of a neural network. Comparing the results from the SpiNNaker system to a conventional double-precision simulation, we find that the network behavior is comparable, and the final weights differ by less than 3% between the two simulations, while the SpiNNaker simulation runs much faster, since it runs in real time, independent of network size.

Abstract

Recent development of neuromorphic hardware offers great potential to speed up simulations of neural networks. SpiNNaker is a neuromorphic hardware and software system designed to be scalable and flexible enough to implement a variety of different types of simulations of neural systems, including spiking simulations with plasticity and learning. Spike-timing dependent plasticity (STDP) rules are the most common form of learning used in spiking networks. However, to date very few such rules have been implemented on SpiNNaker, in part because implementations must be designed to fit the specialized nature of the hardware. Here we explain how general STDP rules can be efficiently implemented in the SpiNNaker system. We give two examples of applications of the implemented rule: learning of a temporal sequence, and balancing inhibition and excitation of a neural network. Comparing the results from the SpiNNaker system to a conventional double-precision simulation, we find that the network behavior is comparable, and the final weights differ by less than 3% between the two simulations, while the SpiNNaker simulation runs much faster, since it runs in real time, independent of network size.

Statistics

Citations

Altmetrics

Downloads

0 downloads since deposited on 25 Feb 2015
0 downloads since 12 months

Additional indexing

Item Type:Conference or Workshop Item (Speech), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Event End Date:11 July 2014
Deposited On:25 Feb 2015 10:33
Last Modified:08 Dec 2017 11:36
Publisher:IEEE Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN)
Series Name:International Joint Conference on Neural Networks (IJCNN)
ISBN:978-1-4799-6627-1
Publisher DOI:https://doi.org/10.1109/IJCNN.2014.6889876

Download