In April 2016 Manchester eScholar was replaced by the University of Manchester’s new Research Information Management System, Pure. In the autumn the University’s research outputs will be available to search and browse via a new Research Portal. Until then the University’s full publication record can be accessed via a temporary portal and the old eScholar content is available to search and browse via this archive.

Parallel Simulation of Neural Networks on SpiNNaker Universal Neuromorphic Hardware

Jin, Xin

[Thesis]. Manchester, UK: The University of Manchester; 2010.

Access to files

Abstract

Artificial neural networks have shown great potential and have attracted much research interest. One problem faced when simulating such networks is speed. As the number of neurons increases, the time to simulate and train a network increases dramatically. This makes it difficult to simulate and train a large-scale network system without the support of a high-performance computer system. The solution we present is a ``real'' parallel system -- using a parallel machine to simulate neural networks which are intrinsically parallel applications.SpiNNaker is a scalable massively-parallel computing system under development with the aim of building a general-purpose platform for the parallel simulation of large-scale neural systems. This research investigates how to model large-scale neural networks efficiently on such a parallel machine. While providing increased overall computational power, a parallel architecture introduces a new problem -- the increased communication reduces the speedup gains. Modeling schemes, which take into account communication, processing, and storage requirements, are investigated to solve this problem. Since modeling schemes are application-dependent, two different types of neural network are examined -- spiking neural networks with spike-time dependent plasticity, and the parallel distributed processing model with the backpropagation learning rule. Different modeling schemes are developed and evaluated for the two types of neural network. The research shows the feasibility of the approach as well as the performance of SpiNNaker as a general-purpose platform for the simulation of neural networks. The linear scalability shown in this architecture provides a path to the further development of parallel solutions for the simulation of extremely large-scale neural networks.

Bibliographic metadata

Type of resource:
Content type:
Form of thesis:
Type of submission:
Degree type:
Doctor of Philosophy
Degree programme:
PhD Computer Science
Publication date:
Location:
Manchester, UK
Total pages:
193
Abstract:
Artificial neural networks have shown great potential and have attracted much research interest. One problem faced when simulating such networks is speed. As the number of neurons increases, the time to simulate and train a network increases dramatically. This makes it difficult to simulate and train a large-scale network system without the support of a high-performance computer system. The solution we present is a ``real'' parallel system -- using a parallel machine to simulate neural networks which are intrinsically parallel applications.SpiNNaker is a scalable massively-parallel computing system under development with the aim of building a general-purpose platform for the parallel simulation of large-scale neural systems. This research investigates how to model large-scale neural networks efficiently on such a parallel machine. While providing increased overall computational power, a parallel architecture introduces a new problem -- the increased communication reduces the speedup gains. Modeling schemes, which take into account communication, processing, and storage requirements, are investigated to solve this problem. Since modeling schemes are application-dependent, two different types of neural network are examined -- spiking neural networks with spike-time dependent plasticity, and the parallel distributed processing model with the backpropagation learning rule. Different modeling schemes are developed and evaluated for the two types of neural network. The research shows the feasibility of the approach as well as the performance of SpiNNaker as a general-purpose platform for the simulation of neural networks. The linear scalability shown in this architecture provides a path to the further development of parallel solutions for the simulation of extremely large-scale neural networks.
Thesis main supervisor(s):
Thesis advisor(s):
Language:
en

Institutional metadata

University researcher(s):

Record metadata

Manchester eScholar ID:
uk-ac-man-scw:85336
Created by:
Jin, Xin
Created:
2nd July, 2010, 12:01:10
Last modified by:
Jin, Xin
Last modified:
6th June, 2011, 18:27:36

Can we help?

The library chat service will be available from 11am-3pm Monday to Friday (excluding Bank Holidays). You can also email your enquiry to us.