Header

UZH-Logo

Maintenance Infos

Unsupervised learning of digit recognition using spike-timing-dependent plasticity


Diehl, P U; Cook, M (2015). Unsupervised learning of digit recognition using spike-timing-dependent plasticity. IEEE Transactions on Neural Networks and Learning Systems, 26(12):2999-3008.

Abstract

The recent development of power-efficient neuromorphic hardware offers great opportunities for applications where power consumption is a main concern, ranging from mobile platforms to server farms. However, it remains a challenging task to design spiking neural networks (SNN) to do pattern recognition on such hardware. We present a SNN for digit recognition which relies on mechanisms commonly used on neuromorphic hardware, i.e. exponential synapses with spiketiming- dependent plasticity, lateral inhibition, and an adaptive threshold. Unlike most other approaches, we do not present any class labels to the network; the network uses unsupervised learning. The performance of our network scales well with the number of neurons used. Intuitively, the used algorithm is comparable to k-means and competitive learning algorithms such as vector quantization and self-organizing maps, each neuron learns a representation of a part of the input space, similar to a centroid in k-means. Our architecture achieves 95% accuracy on the MNIST benchmark, which outperforms other unsupervised learning methods for SNNs. The fact that we used no domainspecific knowledge points toward a more general applicability of the network design.

Abstract

The recent development of power-efficient neuromorphic hardware offers great opportunities for applications where power consumption is a main concern, ranging from mobile platforms to server farms. However, it remains a challenging task to design spiking neural networks (SNN) to do pattern recognition on such hardware. We present a SNN for digit recognition which relies on mechanisms commonly used on neuromorphic hardware, i.e. exponential synapses with spiketiming- dependent plasticity, lateral inhibition, and an adaptive threshold. Unlike most other approaches, we do not present any class labels to the network; the network uses unsupervised learning. The performance of our network scales well with the number of neurons used. Intuitively, the used algorithm is comparable to k-means and competitive learning algorithms such as vector quantization and self-organizing maps, each neuron learns a representation of a part of the input space, similar to a centroid in k-means. Our architecture achieves 95% accuracy on the MNIST benchmark, which outperforms other unsupervised learning methods for SNNs. The fact that we used no domainspecific knowledge points toward a more general applicability of the network design.

Statistics

Citations

Dimensions.ai Metrics
4 citations in Web of Science®
83 citations in Scopus®
129 citations in Microsoft Academic
Google Scholar™

Altmetrics

Downloads

97 downloads since deposited on 25 Feb 2015
36 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, not_refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Date:2015
Deposited On:25 Feb 2015 08:29
Last Modified:14 Feb 2018 08:56
Publisher:Institute of Electrical and Electronics Engineers
ISSN:2162-237X
Additional Information:© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
OA Status:Green
Publisher DOI:https://doi.org/10.1109/TNNLS.2015.2399491

Download

Download PDF  'Unsupervised learning of digit recognition using spike-timing-dependent plasticity'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 654kB
View at publisher