Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network
This paper introduces an event-driven feedforward categorization system, which takes data from a temporal contrast address event representation (AER) sensor. The proposed system extracts bio-inspired cortex-like features and discriminates different patterns using an AER based tempotron classifie...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2015
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/81364 http://hdl.handle.net/10220/39239 |
| _version_ | 1826127572299153408 |
|---|---|
| author | Zhao, Bo Ding, Ruoxi Chen, Shoushun Linares-Barranco, Bernabe Tang, Huajin |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Zhao, Bo Ding, Ruoxi Chen, Shoushun Linares-Barranco, Bernabe Tang, Huajin |
| author_sort | Zhao, Bo |
| collection | NTU |
| description | This paper introduces an event-driven feedforward
categorization system, which takes data from a temporal contrast
address event representation (AER) sensor. The proposed system
extracts bio-inspired cortex-like features and discriminates different
patterns using an AER based tempotron classifier (a network
of Leaky Integrate-and-Fire spiking neurons). One of the system’s
most appealing characteristics is its event-driven processing,
with both input and features taking the form of address events
(spikes). The system was evaluated on an AER posture dataset
and compared to two recently developed bio-inspired models.
Experimental results have shown that it consumes much less
simulation time while still maintaining comparable performance.
In addition, experiments on the Mixed National Institute of Standards
and Technology (MNIST) image dataset have demonstrated
that the proposed system can work not only on raw AER data
but also on images (with a preprocessing step to convert images
into AER events) and that it can maintain competitive accuracy
even when noise is added. The system was further evaluated on
the MNIST-DVS dataset (in which data is recorded using an AER
dynamic vision sensor), with testing accuracy of 88.14%. |
| first_indexed | 2024-10-01T07:10:45Z |
| format | Journal Article |
| id | ntu-10356/81364 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:10:45Z |
| publishDate | 2015 |
| record_format | dspace |
| spelling | ntu-10356/813642020-03-07T13:57:25Z Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network Zhao, Bo Ding, Ruoxi Chen, Shoushun Linares-Barranco, Bernabe Tang, Huajin School of Electrical and Electronic Engineering MNIST Spiking neural network Event driven Feedforward categorization Address event representation (AER) This paper introduces an event-driven feedforward categorization system, which takes data from a temporal contrast address event representation (AER) sensor. The proposed system extracts bio-inspired cortex-like features and discriminates different patterns using an AER based tempotron classifier (a network of Leaky Integrate-and-Fire spiking neurons). One of the system’s most appealing characteristics is its event-driven processing, with both input and features taking the form of address events (spikes). The system was evaluated on an AER posture dataset and compared to two recently developed bio-inspired models. Experimental results have shown that it consumes much less simulation time while still maintaining comparable performance. In addition, experiments on the Mixed National Institute of Standards and Technology (MNIST) image dataset have demonstrated that the proposed system can work not only on raw AER data but also on images (with a preprocessing step to convert images into AER events) and that it can maintain competitive accuracy even when noise is added. The system was further evaluated on the MNIST-DVS dataset (in which data is recorded using an AER dynamic vision sensor), with testing accuracy of 88.14%. Accepted version 2015-12-30T02:23:38Z 2019-12-06T14:29:20Z 2015-12-30T02:23:38Z 2019-12-06T14:29:20Z 2014 Journal Article Zhao, B., Ding, R., Chen, S., Linares-Barranco, B., & Tang, H. (2015). Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network. IEEE Transactions on Neural Networks and Learning Systems, 26(9), 1963-1978. 2162-237X https://hdl.handle.net/10356/81364 http://hdl.handle.net/10220/39239 10.1109/TNNLS.2014.2362542 en IEEE Transactions on Neural Networks and Learning Systems © 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. The published version is available at: [http://dx.doi.org/10.1109/TNNLS.2014.2362542]. 16 p. application/pdf |
| spellingShingle | MNIST Spiking neural network Event driven Feedforward categorization Address event representation (AER) Zhao, Bo Ding, Ruoxi Chen, Shoushun Linares-Barranco, Bernabe Tang, Huajin Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network |
| title | Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network |
| title_full | Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network |
| title_fullStr | Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network |
| title_full_unstemmed | Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network |
| title_short | Feedforward Categorization on AER Motion Events Using Cortex-Like Features in a Spiking Neural Network |
| title_sort | feedforward categorization on aer motion events using cortex like features in a spiking neural network |
| topic | MNIST Spiking neural network Event driven Feedforward categorization Address event representation (AER) |
| url | https://hdl.handle.net/10356/81364 http://hdl.handle.net/10220/39239 |
| work_keys_str_mv | AT zhaobo feedforwardcategorizationonaermotioneventsusingcortexlikefeaturesinaspikingneuralnetwork AT dingruoxi feedforwardcategorizationonaermotioneventsusingcortexlikefeaturesinaspikingneuralnetwork AT chenshoushun feedforwardcategorizationonaermotioneventsusingcortexlikefeaturesinaspikingneuralnetwork AT linaresbarrancobernabe feedforwardcategorizationonaermotioneventsusingcortexlikefeaturesinaspikingneuralnetwork AT tanghuajin feedforwardcategorizationonaermotioneventsusingcortexlikefeaturesinaspikingneuralnetwork |