A bio-inspired feedforward system for categorization of AER motion events

Author

Bo Zhao ; Qiang Yu ; Hang Yu ; Shoushun Chen ; Huajin Tang

Author_Institution

Inst. for Infocomm Res., Agency for Sci., Technol. & Res. (A*STAR), Singapore, Singapore

fYear

2013

fDate

Oct. 31 2013-Nov. 2 2013

Firstpage

9

Lastpage

12

Abstract

This paper introduces an event based feedforward categorization system, which takes data from a temporal contrast Address Event Presentation (AER) sensor. The proposed system extracts bio-inspired cortex-like features and discriminates different patterns using AER based tempotron classifier (a network of leaky integrate-and-fire (LIF) spiking neurons). One appealing character of our system is the event-driven processing. The input and the features are both in the form of address events (spikes). Experimental results on a posture dataset have proved the efficacy of the proposed system.

Keywords

biomechanics; biomedical equipment; biomedical optical imaging; feature extraction; feedforward neural nets; image classification; image motion analysis; medical image processing; AER based tempotron classifier; AER motion event categorization; LIF spiking neuron; bio-inspired cortex-like feature extraction; bio-inspired feedforward system; event based feedforward categorization system; event-driven processing; leaky integrate-and-fire spiking neurons; posture dataset; temporal contrast address event presentation sensor; Architecture; Convolution; Detectors; Feature extraction; Feedforward neural networks; Kernel; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Circuits and Systems Conference (BioCAS), 2013 IEEE

Conference_Location

Rotterdam

Type

conf

DOI

10.1109/BioCAS.2013.6679627

Filename

6679627