Header

UZH-Logo

Maintenance Infos

Improved margin multi-class classification using dendritic neurons with morphological learning


Hussain, S; Liu, S-C; Basu, A (2014). Improved margin multi-class classification using dendritic neurons with morphological learning. In: IEEE International Symposium on Circuits and Systems (ISCAS), Melbourne, Australia, 1 June 2014 - 5 June 2014, 2640- 2643.

Abstract

We present an architecture of a spike based multiclass classifier using neurons with non-linear dendrites and sparse synaptic connectivity where each synapse takes a binary value. The learning in this model happens not through weight updates but through structural changes, i.e. a change of connectivity between inputs and dendrites. Hence, it is well suited for implementation in neuromorphic systems using address event representation (AER). We present a new learning rule that allows better generalization of the system to noisy testing data making it feasible to transfer learnt weights in software to a hardware device interfacing with noisy spiking sensors. The new rule improves testing accuracy by 7 - 10% compared to earlier versions. We also present preliminary results for multi-class classification on handwritten digits from the MNIST database and show that our system can attain comparable performance (≈ 3% more error) with other reported spike based classifiers while using at least 50% less synaptic resources.

Abstract

We present an architecture of a spike based multiclass classifier using neurons with non-linear dendrites and sparse synaptic connectivity where each synapse takes a binary value. The learning in this model happens not through weight updates but through structural changes, i.e. a change of connectivity between inputs and dendrites. Hence, it is well suited for implementation in neuromorphic systems using address event representation (AER). We present a new learning rule that allows better generalization of the system to noisy testing data making it feasible to transfer learnt weights in software to a hardware device interfacing with noisy spiking sensors. The new rule improves testing accuracy by 7 - 10% compared to earlier versions. We also present preliminary results for multi-class classification on handwritten digits from the MNIST database and show that our system can attain comparable performance (≈ 3% more error) with other reported spike based classifiers while using at least 50% less synaptic resources.

Statistics

Citations

5 citations in Web of Science®
7 citations in Scopus®
Google Scholar™

Altmetrics

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:5 June 2014
Deposited On:25 Feb 2015 10:37
Last Modified:16 Aug 2017 00:15
Publisher:Proceedings of the 2014 IEEE International Symposium on Circuits and Systems (ISCAS)
Series Name:2014 IEEE International Symposium on Circuits and Systems
ISBN:978-1-4799-3431-7
Publisher DOI:https://doi.org/10.1109/ISCAS.2014.6865715

Download

Full text not available from this repository.
View at publisher