SEFRON : a new spiking neuron model with time-varying synaptic efficacy function for pattern classification
This paper presents a new time-varying long-term Synaptic Efficacy Function-based leaky-integrate-and-fire neuRON model, referred to as SEFRON and its supervised learning rule for pattern classification problems. The time-varying synaptic efficacy function is represented by a sum of amplitude modula...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/144620 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-144620 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1446202020-11-16T04:34:03Z SEFRON : a new spiking neuron model with time-varying synaptic efficacy function for pattern classification Jeyasothy, Abeegithan Sundaram, Suresh Sundararajan, Narasimhan School of Computer Science and Engineering Engineering::Computer science and engineering Gamma-aminobutyric Acid (GABA)-switch This paper presents a new time-varying long-term Synaptic Efficacy Function-based leaky-integrate-and-fire neuRON model, referred to as SEFRON and its supervised learning rule for pattern classification problems. The time-varying synaptic efficacy function is represented by a sum of amplitude modulated Gaussian distribution functions located at different times. For a given pattern, the SEFRON's learning rule determines the changes in the amplitudes of weights at selected presynaptic spike times by minimizing a new error function reflecting the differences between the desired and actual postsynaptic firing times. Similar to the gamma-aminobutyric acid-switch phenomenon observed in a biological neuron that switches between excitatory and inhibitory postsynaptic potentials based on the physiological needs, the time-varying synapse model proposed in this paper allows the synaptic efficacy (weight) to switch signs in a continuous manner. The computational power and the functioning of SEFRON are first illustrated using a binary pattern classification problem. The detailed performance comparisons of a single SEFRON classifier with other spiking neural networks (SNNs) are also presented using four benchmark data sets from the UCI machine learning repository. The results clearly indicate that a single SEFRON provides a similar generalization performance compared to other SNNs with multiple layers and multiple neurons. Accepted version 2020-11-16T04:34:03Z 2020-11-16T04:34:03Z 2019 Journal Article Jeyasothy, A., Sundaram, S., & Sundararajan, N. (2019). SEFRON : A New Spiking Neuron Model With Time-Varying Synaptic Efficacy Function for Pattern Classification. IEEE Transactions on Neural Networks and Learning Systems, 30(4), 1231–1240. doi:10.1109/tnnls.2018.2868874 2162-237X https://hdl.handle.net/10356/144620 10.1109/TNNLS.2018.2868874 30273156 4 30 1231 1240 en IEEE transactions on neural networks and learning systems © 2018 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. The published version is available at: https://doi.org/10.1109/TNNLS.2018.2868874. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Gamma-aminobutyric Acid (GABA)-switch |
spellingShingle |
Engineering::Computer science and engineering Gamma-aminobutyric Acid (GABA)-switch Jeyasothy, Abeegithan Sundaram, Suresh Sundararajan, Narasimhan SEFRON : a new spiking neuron model with time-varying synaptic efficacy function for pattern classification |
description |
This paper presents a new time-varying long-term Synaptic Efficacy Function-based leaky-integrate-and-fire neuRON model, referred to as SEFRON and its supervised learning rule for pattern classification problems. The time-varying synaptic efficacy function is represented by a sum of amplitude modulated Gaussian distribution functions located at different times. For a given pattern, the SEFRON's learning rule determines the changes in the amplitudes of weights at selected presynaptic spike times by minimizing a new error function reflecting the differences between the desired and actual postsynaptic firing times. Similar to the gamma-aminobutyric acid-switch phenomenon observed in a biological neuron that switches between excitatory and inhibitory postsynaptic potentials based on the physiological needs, the time-varying synapse model proposed in this paper allows the synaptic efficacy (weight) to switch signs in a continuous manner. The computational power and the functioning of SEFRON are first illustrated using a binary pattern classification problem. The detailed performance comparisons of a single SEFRON classifier with other spiking neural networks (SNNs) are also presented using four benchmark data sets from the UCI machine learning repository. The results clearly indicate that a single SEFRON provides a similar generalization performance compared to other SNNs with multiple layers and multiple neurons. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Jeyasothy, Abeegithan Sundaram, Suresh Sundararajan, Narasimhan |
format |
Article |
author |
Jeyasothy, Abeegithan Sundaram, Suresh Sundararajan, Narasimhan |
author_sort |
Jeyasothy, Abeegithan |
title |
SEFRON : a new spiking neuron model with time-varying synaptic efficacy function for pattern classification |
title_short |
SEFRON : a new spiking neuron model with time-varying synaptic efficacy function for pattern classification |
title_full |
SEFRON : a new spiking neuron model with time-varying synaptic efficacy function for pattern classification |
title_fullStr |
SEFRON : a new spiking neuron model with time-varying synaptic efficacy function for pattern classification |
title_full_unstemmed |
SEFRON : a new spiking neuron model with time-varying synaptic efficacy function for pattern classification |
title_sort |
sefron : a new spiking neuron model with time-varying synaptic efficacy function for pattern classification |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/144620 |
_version_ |
1688665340654911488 |