Bugs

A real-time adaptive network that responds to motion

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

Abstract

Summary form only given, as follows. Bugs is an artificial neural system which detects motion in an external environment and can be trained by a teacher to react according to a desired strategy. System elements are a hard-wired motion detection network and an adaptive controller network. The motion detection net is based on a model of motion-sensitive ganglia found in rabbit eyes, while the controller learns strategies from a teacher in the form of finite-state transitions. Bugs's subnetworks are integrated by continuous-time dynamics, and elements are synchronized through simple time-scaling parameters. The author reports two experiments in which Bugs learned quite different responses to moving objects.

Original languageEnglish (US)
Title of host publicationIJCNN Int Jt Conf Neural Network
Editors Anon
PublisherPubl by IEEE
Pages622
Number of pages1
StatePublished - 1989
Externally publishedYes
EventIJCNN International Joint Conference on Neural Networks - Washington, DC, USA
Duration: Jun 18 1989Jun 22 1989

Other

OtherIJCNN International Joint Conference on Neural Networks
CityWashington, DC, USA
Period6/18/896/22/89

Fingerprint

Controllers
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Winter, C. L. (1989). Bugs: A real-time adaptive network that responds to motion. In Anon (Ed.), IJCNN Int Jt Conf Neural Network (pp. 622). Publ by IEEE.

Bugs : A real-time adaptive network that responds to motion. / Winter, C Larrabee.

IJCNN Int Jt Conf Neural Network. ed. / Anon. Publ by IEEE, 1989. p. 622.

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

Winter, CL 1989, Bugs: A real-time adaptive network that responds to motion. in Anon (ed.), IJCNN Int Jt Conf Neural Network. Publ by IEEE, pp. 622, IJCNN International Joint Conference on Neural Networks, Washington, DC, USA, 6/18/89.
Winter CL. Bugs: A real-time adaptive network that responds to motion. In Anon, editor, IJCNN Int Jt Conf Neural Network. Publ by IEEE. 1989. p. 622
Winter, C Larrabee. / Bugs : A real-time adaptive network that responds to motion. IJCNN Int Jt Conf Neural Network. editor / Anon. Publ by IEEE, 1989. pp. 622
@inproceedings{430dd55d822547d5be44efd530603166,
title = "Bugs: A real-time adaptive network that responds to motion",
abstract = "Summary form only given, as follows. Bugs is an artificial neural system which detects motion in an external environment and can be trained by a teacher to react according to a desired strategy. System elements are a hard-wired motion detection network and an adaptive controller network. The motion detection net is based on a model of motion-sensitive ganglia found in rabbit eyes, while the controller learns strategies from a teacher in the form of finite-state transitions. Bugs's subnetworks are integrated by continuous-time dynamics, and elements are synchronized through simple time-scaling parameters. The author reports two experiments in which Bugs learned quite different responses to moving objects.",
author = "Winter, {C Larrabee}",
year = "1989",
language = "English (US)",
pages = "622",
editor = "Anon",
booktitle = "IJCNN Int Jt Conf Neural Network",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Bugs

T2 - A real-time adaptive network that responds to motion

AU - Winter, C Larrabee

PY - 1989

Y1 - 1989

N2 - Summary form only given, as follows. Bugs is an artificial neural system which detects motion in an external environment and can be trained by a teacher to react according to a desired strategy. System elements are a hard-wired motion detection network and an adaptive controller network. The motion detection net is based on a model of motion-sensitive ganglia found in rabbit eyes, while the controller learns strategies from a teacher in the form of finite-state transitions. Bugs's subnetworks are integrated by continuous-time dynamics, and elements are synchronized through simple time-scaling parameters. The author reports two experiments in which Bugs learned quite different responses to moving objects.

AB - Summary form only given, as follows. Bugs is an artificial neural system which detects motion in an external environment and can be trained by a teacher to react according to a desired strategy. System elements are a hard-wired motion detection network and an adaptive controller network. The motion detection net is based on a model of motion-sensitive ganglia found in rabbit eyes, while the controller learns strategies from a teacher in the form of finite-state transitions. Bugs's subnetworks are integrated by continuous-time dynamics, and elements are synchronized through simple time-scaling parameters. The author reports two experiments in which Bugs learned quite different responses to moving objects.

UR - http://www.scopus.com/inward/record.url?scp=0024928534&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024928534&partnerID=8YFLogxK

M3 - Conference contribution

SP - 622

BT - IJCNN Int Jt Conf Neural Network

A2 - Anon, null

PB - Publ by IEEE

ER -