Adaptive network that flees pursuit

Research output: Contribution to journalArticle

Abstract

We describe a hierarchical artificial neural system (ANS) that learns to flee predators in a world without obstacles. The ANS is composed of a motion detection network (MD) an adaptive controller and body. Currently we simulate the activity of the body. The network operates in continuous time and is controlled solely through the activities of nodes. The controller obtains sensory information from MD in the form of reduced resolution maps of motion in the prey's visual field and determines a desirable next position by evaluating both motion information and the prey's current position as obtained from the body. The next position is passed as a goal, or instruction, to the body which moves accordingly.

Original languageEnglish (US)
Pages (from-to)367
Number of pages1
JournalNeural Networks
Volume1
Issue number1 SUPPL
DOIs
StatePublished - 1988
Externally publishedYes

Fingerprint

Controllers
Visual Fields

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Cite this

Adaptive network that flees pursuit. / Winter, C Larrabee.

In: Neural Networks, Vol. 1, No. 1 SUPPL, 1988, p. 367.

Research output: Contribution to journalArticle

Winter, C Larrabee. / Adaptive network that flees pursuit. In: Neural Networks. 1988 ; Vol. 1, No. 1 SUPPL. pp. 367.
@article{61b54c99046e4e0b8aedba6d010d8aa2,
title = "Adaptive network that flees pursuit",
abstract = "We describe a hierarchical artificial neural system (ANS) that learns to flee predators in a world without obstacles. The ANS is composed of a motion detection network (MD) an adaptive controller and body. Currently we simulate the activity of the body. The network operates in continuous time and is controlled solely through the activities of nodes. The controller obtains sensory information from MD in the form of reduced resolution maps of motion in the prey's visual field and determines a desirable next position by evaluating both motion information and the prey's current position as obtained from the body. The next position is passed as a goal, or instruction, to the body which moves accordingly.",
author = "Winter, {C Larrabee}",
year = "1988",
doi = "10.1016/0893-6080(88)90395-4",
language = "English (US)",
volume = "1",
pages = "367",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "1 SUPPL",

}

TY - JOUR

T1 - Adaptive network that flees pursuit

AU - Winter, C Larrabee

PY - 1988

Y1 - 1988

N2 - We describe a hierarchical artificial neural system (ANS) that learns to flee predators in a world without obstacles. The ANS is composed of a motion detection network (MD) an adaptive controller and body. Currently we simulate the activity of the body. The network operates in continuous time and is controlled solely through the activities of nodes. The controller obtains sensory information from MD in the form of reduced resolution maps of motion in the prey's visual field and determines a desirable next position by evaluating both motion information and the prey's current position as obtained from the body. The next position is passed as a goal, or instruction, to the body which moves accordingly.

AB - We describe a hierarchical artificial neural system (ANS) that learns to flee predators in a world without obstacles. The ANS is composed of a motion detection network (MD) an adaptive controller and body. Currently we simulate the activity of the body. The network operates in continuous time and is controlled solely through the activities of nodes. The controller obtains sensory information from MD in the form of reduced resolution maps of motion in the prey's visual field and determines a desirable next position by evaluating both motion information and the prey's current position as obtained from the body. The next position is passed as a goal, or instruction, to the body which moves accordingly.

UR - http://www.scopus.com/inward/record.url?scp=0024178257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024178257&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90395-4

DO - 10.1016/0893-6080(88)90395-4

M3 - Article

VL - 1

SP - 367

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 1 SUPPL

ER -