DESKNET: The dermatology expert system with knowledge-based network

Youngohc Yoon, Lynn L. Peterson, Paul R. Bergstresser

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A prototypical connectionist expert system is presented. DESKNET is built for ultimate use in the instruction of medical students to diagnose papulosquamous skin diseases. DESKNET is an ES composed of a three layered back propagation network consisting of an input layer, a hidden layer, and an output layer. The units on a layer have excitatory or inhibitory connections to units on the adjacent layers. Input for the system is a list of symptoms organized by 18 parameters. The back propagation algorithm encodes the implicit 'knowledge' such that it remains in an implicit form; thus, more knowledge can be captured. Therefore, the back propagation model appears to be a useful tool for representing concepts of a domain and encoding them in a network. Limitations of the algorithm are identified.

Original languageEnglish (US)
Pages (from-to)477
Number of pages1
JournalNeural Networks
Volume1
Issue number1 SUPPL
DOIs
StatePublished - 1988

Fingerprint

Dermatology
Expert Systems
Backpropagation
Expert systems
Papulosquamous Skin Diseases
Backpropagation algorithms
Medical Students
Skin
Students

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Cite this

DESKNET : The dermatology expert system with knowledge-based network. / Yoon, Youngohc; Peterson, Lynn L.; Bergstresser, Paul R.

In: Neural Networks, Vol. 1, No. 1 SUPPL, 1988, p. 477.

Research output: Contribution to journalArticle

Yoon, Youngohc ; Peterson, Lynn L. ; Bergstresser, Paul R. / DESKNET : The dermatology expert system with knowledge-based network. In: Neural Networks. 1988 ; Vol. 1, No. 1 SUPPL. pp. 477.
@article{ce5626abaf5b4cbb824e222d49f7390a,
title = "DESKNET: The dermatology expert system with knowledge-based network",
abstract = "A prototypical connectionist expert system is presented. DESKNET is built for ultimate use in the instruction of medical students to diagnose papulosquamous skin diseases. DESKNET is an ES composed of a three layered back propagation network consisting of an input layer, a hidden layer, and an output layer. The units on a layer have excitatory or inhibitory connections to units on the adjacent layers. Input for the system is a list of symptoms organized by 18 parameters. The back propagation algorithm encodes the implicit 'knowledge' such that it remains in an implicit form; thus, more knowledge can be captured. Therefore, the back propagation model appears to be a useful tool for representing concepts of a domain and encoding them in a network. Limitations of the algorithm are identified.",
author = "Youngohc Yoon and Peterson, {Lynn L.} and Bergstresser, {Paul R.}",
year = "1988",
doi = "10.1016/0893-6080(88)90501-1",
language = "English (US)",
volume = "1",
pages = "477",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "1 SUPPL",

}

TY - JOUR

T1 - DESKNET

T2 - The dermatology expert system with knowledge-based network

AU - Yoon, Youngohc

AU - Peterson, Lynn L.

AU - Bergstresser, Paul R.

PY - 1988

Y1 - 1988

N2 - A prototypical connectionist expert system is presented. DESKNET is built for ultimate use in the instruction of medical students to diagnose papulosquamous skin diseases. DESKNET is an ES composed of a three layered back propagation network consisting of an input layer, a hidden layer, and an output layer. The units on a layer have excitatory or inhibitory connections to units on the adjacent layers. Input for the system is a list of symptoms organized by 18 parameters. The back propagation algorithm encodes the implicit 'knowledge' such that it remains in an implicit form; thus, more knowledge can be captured. Therefore, the back propagation model appears to be a useful tool for representing concepts of a domain and encoding them in a network. Limitations of the algorithm are identified.

AB - A prototypical connectionist expert system is presented. DESKNET is built for ultimate use in the instruction of medical students to diagnose papulosquamous skin diseases. DESKNET is an ES composed of a three layered back propagation network consisting of an input layer, a hidden layer, and an output layer. The units on a layer have excitatory or inhibitory connections to units on the adjacent layers. Input for the system is a list of symptoms organized by 18 parameters. The back propagation algorithm encodes the implicit 'knowledge' such that it remains in an implicit form; thus, more knowledge can be captured. Therefore, the back propagation model appears to be a useful tool for representing concepts of a domain and encoding them in a network. Limitations of the algorithm are identified.

UR - http://www.scopus.com/inward/record.url?scp=0024177529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024177529&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90501-1

DO - 10.1016/0893-6080(88)90501-1

M3 - Article

AN - SCOPUS:0024177529

VL - 1

SP - 477

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 1 SUPPL

ER -