Using a neural network to determine fitness in genetic design

Jun Zhang, Shane Farritor

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Many automated design approaches require an objective function to determine the quality of a given design. Often, this function is a complex relationship between many parameters that are subjective, and their relationships are difficult to quantify. This article presents a neural network based method to solve the inverse problem of determining the designer's preferences. In the forward problem, the designer would define relative preferences and the relationship between performance attributes for a given design task. The quality of a design could then be evaluated based on these preferences. The inverse problem seeks to quantify the designer's preferences and the relationships between those preferences based on evaluations of a few candidate designs. Generally, a human designer might propose candidate designs, the designer would then rank or rate the quality of the candidate designs, and then the candidate designs are used to solve the inverse problem by training a neural network fitness function. This fitness function can then be used to evaluate and create new designs that the human designer might not conceive. This article demonstrates the approach through the design of modular robots for planetary exploration.

Original languageEnglish (US)
Pages (from-to)629-642
Number of pages14
JournalInverse Problems in Science and Engineering
Volume12
Issue number6 SPEC. ISS.
DOIs
StatePublished - Dec 1 2004

Fingerprint

Fitness
Neural Networks
Neural networks
Inverse problems
Inverse Problem
Fitness Function
Quantify
Design
Modular robots
Forward Problem
Objective function
Robot
Attribute
Relationships
Evaluate
Evaluation

Keywords

  • Design preferences
  • Genetic design
  • Modular robotics
  • Planetary robotics

ASJC Scopus subject areas

  • Engineering(all)
  • Computer Science Applications
  • Applied Mathematics

Cite this

Using a neural network to determine fitness in genetic design. / Zhang, Jun; Farritor, Shane.

In: Inverse Problems in Science and Engineering, Vol. 12, No. 6 SPEC. ISS., 01.12.2004, p. 629-642.

Research output: Contribution to journalArticle

@article{b1030b555e9a496499b45159a380214e,
title = "Using a neural network to determine fitness in genetic design",
abstract = "Many automated design approaches require an objective function to determine the quality of a given design. Often, this function is a complex relationship between many parameters that are subjective, and their relationships are difficult to quantify. This article presents a neural network based method to solve the inverse problem of determining the designer's preferences. In the forward problem, the designer would define relative preferences and the relationship between performance attributes for a given design task. The quality of a design could then be evaluated based on these preferences. The inverse problem seeks to quantify the designer's preferences and the relationships between those preferences based on evaluations of a few candidate designs. Generally, a human designer might propose candidate designs, the designer would then rank or rate the quality of the candidate designs, and then the candidate designs are used to solve the inverse problem by training a neural network fitness function. This fitness function can then be used to evaluate and create new designs that the human designer might not conceive. This article demonstrates the approach through the design of modular robots for planetary exploration.",
keywords = "Design preferences, Genetic design, Modular robotics, Planetary robotics",
author = "Jun Zhang and Shane Farritor",
year = "2004",
month = "12",
day = "1",
doi = "10.1080/1068276042000207267",
language = "English (US)",
volume = "12",
pages = "629--642",
journal = "Inverse Problems in Science and Engineering",
issn = "1741-5977",
publisher = "Taylor and Francis Ltd.",
number = "6 SPEC. ISS.",

}

TY - JOUR

T1 - Using a neural network to determine fitness in genetic design

AU - Zhang, Jun

AU - Farritor, Shane

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Many automated design approaches require an objective function to determine the quality of a given design. Often, this function is a complex relationship between many parameters that are subjective, and their relationships are difficult to quantify. This article presents a neural network based method to solve the inverse problem of determining the designer's preferences. In the forward problem, the designer would define relative preferences and the relationship between performance attributes for a given design task. The quality of a design could then be evaluated based on these preferences. The inverse problem seeks to quantify the designer's preferences and the relationships between those preferences based on evaluations of a few candidate designs. Generally, a human designer might propose candidate designs, the designer would then rank or rate the quality of the candidate designs, and then the candidate designs are used to solve the inverse problem by training a neural network fitness function. This fitness function can then be used to evaluate and create new designs that the human designer might not conceive. This article demonstrates the approach through the design of modular robots for planetary exploration.

AB - Many automated design approaches require an objective function to determine the quality of a given design. Often, this function is a complex relationship between many parameters that are subjective, and their relationships are difficult to quantify. This article presents a neural network based method to solve the inverse problem of determining the designer's preferences. In the forward problem, the designer would define relative preferences and the relationship between performance attributes for a given design task. The quality of a design could then be evaluated based on these preferences. The inverse problem seeks to quantify the designer's preferences and the relationships between those preferences based on evaluations of a few candidate designs. Generally, a human designer might propose candidate designs, the designer would then rank or rate the quality of the candidate designs, and then the candidate designs are used to solve the inverse problem by training a neural network fitness function. This fitness function can then be used to evaluate and create new designs that the human designer might not conceive. This article demonstrates the approach through the design of modular robots for planetary exploration.

KW - Design preferences

KW - Genetic design

KW - Modular robotics

KW - Planetary robotics

UR - http://www.scopus.com/inward/record.url?scp=4944256638&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4944256638&partnerID=8YFLogxK

U2 - 10.1080/1068276042000207267

DO - 10.1080/1068276042000207267

M3 - Article

AN - SCOPUS:4944256638

VL - 12

SP - 629

EP - 642

JO - Inverse Problems in Science and Engineering

JF - Inverse Problems in Science and Engineering

SN - 1741-5977

IS - 6 SPEC. ISS.

ER -