Bio-inspired categorization using event-driven feature extraction and spike-based learning
This paper presents a fully event-driven feedforward architecture that accounts for rapid categorization. The proposed algorithm processes the address event data generated either from an image or from Address-Event-Representation (AER) temporal contrast vision sensor. Bio-inspired, cortex-like,...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2014
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/103456 http://hdl.handle.net/10220/24499 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-103456 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1034562020-03-07T13:24:51Z Bio-inspired categorization using event-driven feature extraction and spike-based learning Zhao, Bo Chen, Shoushun Tang, Huajin School of Electrical and Electronic Engineering 2014 International Joint Conference on Neural Networks (IJCNN) DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems This paper presents a fully event-driven feedforward architecture that accounts for rapid categorization. The proposed algorithm processes the address event data generated either from an image or from Address-Event-Representation (AER) temporal contrast vision sensor. Bio-inspired, cortex-like, spikebased features are obtained through event-driven convolution and neural competition. The extracted spike feature patterns are then classified by a network of leaky integrate-and-fire (LIF) spiking neurons, in which the weights are trained using tempotron learning rule. One appealing characteristic of our system is the fully event-driven processing. The input, the features, and the classification are all based on address events (spikes). Experimental results on three datasets have proved the efficacy of the proposed algorithm. Accepted version 2014-12-22T01:30:33Z 2019-12-06T21:13:06Z 2014-12-22T01:30:33Z 2019-12-06T21:13:06Z 2014 2014 Conference Paper Zhao, B., Chen, S., & Tang, H. (2014). Bio-inspired categorization using event-driven feature extraction and spike-based learning. 2014 International Joint Conference on Neural Networks (IJCNN), 3845-3852. https://hdl.handle.net/10356/103456 http://hdl.handle.net/10220/24499 10.1109/IJCNN.2014.6889541 en © 2014 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: [Article DOI: http://dx.doi.org/10.1109/IJCNN.2014.6889541]. 8 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems |
spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems Zhao, Bo Chen, Shoushun Tang, Huajin Bio-inspired categorization using event-driven feature extraction and spike-based learning |
description |
This paper presents a fully event-driven feedforward
architecture that accounts for rapid categorization. The proposed
algorithm processes the address event data generated either
from an image or from Address-Event-Representation (AER)
temporal contrast vision sensor. Bio-inspired, cortex-like, spikebased
features are obtained through event-driven convolution
and neural competition. The extracted spike feature patterns
are then classified by a network of leaky integrate-and-fire
(LIF) spiking neurons, in which the weights are trained using
tempotron learning rule. One appealing characteristic of our
system is the fully event-driven processing. The input, the
features, and the classification are all based on address events
(spikes). Experimental results on three datasets have proved the efficacy of the proposed algorithm. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Zhao, Bo Chen, Shoushun Tang, Huajin |
format |
Conference or Workshop Item |
author |
Zhao, Bo Chen, Shoushun Tang, Huajin |
author_sort |
Zhao, Bo |
title |
Bio-inspired categorization using event-driven feature extraction and spike-based learning |
title_short |
Bio-inspired categorization using event-driven feature extraction and spike-based learning |
title_full |
Bio-inspired categorization using event-driven feature extraction and spike-based learning |
title_fullStr |
Bio-inspired categorization using event-driven feature extraction and spike-based learning |
title_full_unstemmed |
Bio-inspired categorization using event-driven feature extraction and spike-based learning |
title_sort |
bio-inspired categorization using event-driven feature extraction and spike-based learning |
publishDate |
2014 |
url |
https://hdl.handle.net/10356/103456 http://hdl.handle.net/10220/24499 |
_version_ |
1681048715467423744 |