Biologically-inspired spiking neural networks with Hebbian learning for vision processing

Lyle Norman Long, Ankur Gupta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

This paper describes our recent efforts to develop biologically-inspired spiking neural network software (called JSpike) for vision processing. The ultimate goal is object recognition with both scale and translational invariance. This paper describes the initial software development effort, including code performance and memory requirement results. The software includes the neural network, image capture code, and graphical display programs. All the software is written in Java. The CPU time requirements for very large networks scale with the number of synapses, but even on a laptop computer billions of synapses can be simulated. While our initial application is image processing, the software is written to be very general and usable for processing other sensor data and for data fusion.

Original languageEnglish (US)
Title of host publication46th AIAA Aerospace Sciences Meeting and Exhibit
StatePublished - Dec 1 2008
Event46th AIAA Aerospace Sciences Meeting and Exhibit - Reno, NV, United States
Duration: Jan 7 2008Jan 10 2008

Other

Other46th AIAA Aerospace Sciences Meeting and Exhibit
CountryUnited States
CityReno, NV
Period1/7/081/10/08

Fingerprint

Neural networks
Processing
Laptop computers
Object recognition
Data fusion
Invariance
Program processors
Software engineering
Image processing
Display devices
Data storage equipment
Sensors

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering

Cite this

Long, L. N., & Gupta, A. (2008). Biologically-inspired spiking neural networks with Hebbian learning for vision processing. In 46th AIAA Aerospace Sciences Meeting and Exhibit [2008-0885]
Long, Lyle Norman ; Gupta, Ankur. / Biologically-inspired spiking neural networks with Hebbian learning for vision processing. 46th AIAA Aerospace Sciences Meeting and Exhibit. 2008.
@inproceedings{89ffcdfdd3d8420980959a9b9c8e533b,
title = "Biologically-inspired spiking neural networks with Hebbian learning for vision processing",
abstract = "This paper describes our recent efforts to develop biologically-inspired spiking neural network software (called JSpike) for vision processing. The ultimate goal is object recognition with both scale and translational invariance. This paper describes the initial software development effort, including code performance and memory requirement results. The software includes the neural network, image capture code, and graphical display programs. All the software is written in Java. The CPU time requirements for very large networks scale with the number of synapses, but even on a laptop computer billions of synapses can be simulated. While our initial application is image processing, the software is written to be very general and usable for processing other sensor data and for data fusion.",
author = "Long, {Lyle Norman} and Ankur Gupta",
year = "2008",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781563479373",
booktitle = "46th AIAA Aerospace Sciences Meeting and Exhibit",

}

Long, LN & Gupta, A 2008, Biologically-inspired spiking neural networks with Hebbian learning for vision processing. in 46th AIAA Aerospace Sciences Meeting and Exhibit., 2008-0885, 46th AIAA Aerospace Sciences Meeting and Exhibit, Reno, NV, United States, 1/7/08.

Biologically-inspired spiking neural networks with Hebbian learning for vision processing. / Long, Lyle Norman; Gupta, Ankur.

46th AIAA Aerospace Sciences Meeting and Exhibit. 2008. 2008-0885.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Biologically-inspired spiking neural networks with Hebbian learning for vision processing

AU - Long, Lyle Norman

AU - Gupta, Ankur

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper describes our recent efforts to develop biologically-inspired spiking neural network software (called JSpike) for vision processing. The ultimate goal is object recognition with both scale and translational invariance. This paper describes the initial software development effort, including code performance and memory requirement results. The software includes the neural network, image capture code, and graphical display programs. All the software is written in Java. The CPU time requirements for very large networks scale with the number of synapses, but even on a laptop computer billions of synapses can be simulated. While our initial application is image processing, the software is written to be very general and usable for processing other sensor data and for data fusion.

AB - This paper describes our recent efforts to develop biologically-inspired spiking neural network software (called JSpike) for vision processing. The ultimate goal is object recognition with both scale and translational invariance. This paper describes the initial software development effort, including code performance and memory requirement results. The software includes the neural network, image capture code, and graphical display programs. All the software is written in Java. The CPU time requirements for very large networks scale with the number of synapses, but even on a laptop computer billions of synapses can be simulated. While our initial application is image processing, the software is written to be very general and usable for processing other sensor data and for data fusion.

UR - http://www.scopus.com/inward/record.url?scp=78149462239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149462239&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781563479373

BT - 46th AIAA Aerospace Sciences Meeting and Exhibit

ER -

Long LN, Gupta A. Biologically-inspired spiking neural networks with Hebbian learning for vision processing. In 46th AIAA Aerospace Sciences Meeting and Exhibit. 2008. 2008-0885