Visual Attention Control using Pulse Neural Network with Short Term Synaptic Depression

Koichiro Takita, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a new artificial pulse neural network model which utilizes short term synaptic depression (STSD) for attention control. Compared with classic integrator-type neurons, pulse neurons are known for their superior ability to handle temporal information, as well as the easiness to implement new found properties of biological neurons. STSD is one of such properties. While recent researches indicate that STSD shows some interesting behaviours like gain controls, its usefulness for artificial neural networks is still unclear. The proposed model is a brand new pulse neural network to utilize STSD for movie processing. This model is composed of four layers of pulse neurons. The input is the brightness information of the current image of the movie, and the output is the area which requires system's attention. Due to STSD between the input layer and the first hidden layer, it is capable of keeping its attention on things like fast moving objects, while ignoring static or slow objects even if they are flickering. Experimental results show that this model has the basic abilities for attention control.

Original languageEnglish
Pages (from-to)321-328
Number of pages8
JournalIEEJ Transactions on Electronics, Information and Systems
Volume125
Issue number2
DOIs
Publication statusPublished - 2005

Fingerprint

Neurons
Neural networks
Flickering
Gain control
Luminance
Processing

Keywords

  • movie processing
  • short term synaptic depression
  • Spiking neuron
  • visual attention control

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Visual Attention Control using Pulse Neural Network with Short Term Synaptic Depression. / Takita, Koichiro; Hagiwara, Masafumi.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 125, No. 2, 2005, p. 321-328.

Research output: Contribution to journalArticle

@article{20a23a2cd05e43a7a8b58acd700772a3,
title = "Visual Attention Control using Pulse Neural Network with Short Term Synaptic Depression",
abstract = "In this paper, we propose a new artificial pulse neural network model which utilizes short term synaptic depression (STSD) for attention control. Compared with classic integrator-type neurons, pulse neurons are known for their superior ability to handle temporal information, as well as the easiness to implement new found properties of biological neurons. STSD is one of such properties. While recent researches indicate that STSD shows some interesting behaviours like gain controls, its usefulness for artificial neural networks is still unclear. The proposed model is a brand new pulse neural network to utilize STSD for movie processing. This model is composed of four layers of pulse neurons. The input is the brightness information of the current image of the movie, and the output is the area which requires system's attention. Due to STSD between the input layer and the first hidden layer, it is capable of keeping its attention on things like fast moving objects, while ignoring static or slow objects even if they are flickering. Experimental results show that this model has the basic abilities for attention control.",
keywords = "movie processing, short term synaptic depression, Spiking neuron, visual attention control",
author = "Koichiro Takita and Masafumi Hagiwara",
year = "2005",
doi = "10.1541/ieejeiss.125.321",
language = "English",
volume = "125",
pages = "321--328",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "2",

}

TY - JOUR

T1 - Visual Attention Control using Pulse Neural Network with Short Term Synaptic Depression

AU - Takita, Koichiro

AU - Hagiwara, Masafumi

PY - 2005

Y1 - 2005

N2 - In this paper, we propose a new artificial pulse neural network model which utilizes short term synaptic depression (STSD) for attention control. Compared with classic integrator-type neurons, pulse neurons are known for their superior ability to handle temporal information, as well as the easiness to implement new found properties of biological neurons. STSD is one of such properties. While recent researches indicate that STSD shows some interesting behaviours like gain controls, its usefulness for artificial neural networks is still unclear. The proposed model is a brand new pulse neural network to utilize STSD for movie processing. This model is composed of four layers of pulse neurons. The input is the brightness information of the current image of the movie, and the output is the area which requires system's attention. Due to STSD between the input layer and the first hidden layer, it is capable of keeping its attention on things like fast moving objects, while ignoring static or slow objects even if they are flickering. Experimental results show that this model has the basic abilities for attention control.

AB - In this paper, we propose a new artificial pulse neural network model which utilizes short term synaptic depression (STSD) for attention control. Compared with classic integrator-type neurons, pulse neurons are known for their superior ability to handle temporal information, as well as the easiness to implement new found properties of biological neurons. STSD is one of such properties. While recent researches indicate that STSD shows some interesting behaviours like gain controls, its usefulness for artificial neural networks is still unclear. The proposed model is a brand new pulse neural network to utilize STSD for movie processing. This model is composed of four layers of pulse neurons. The input is the brightness information of the current image of the movie, and the output is the area which requires system's attention. Due to STSD between the input layer and the first hidden layer, it is capable of keeping its attention on things like fast moving objects, while ignoring static or slow objects even if they are flickering. Experimental results show that this model has the basic abilities for attention control.

KW - movie processing

KW - short term synaptic depression

KW - Spiking neuron

KW - visual attention control

UR - http://www.scopus.com/inward/record.url?scp=85024740331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024740331&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.125.321

DO - 10.1541/ieejeiss.125.321

M3 - Article

AN - SCOPUS:85024740331

VL - 125

SP - 321

EP - 328

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 2

ER -