Exploring biases between human and machine generated designs

Christian E. Lopez, Scarlett Rae Miller, Conrad S. Tucker

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The objective of this work is to explore the possible biases that individuals may have toward the perceived functionality of machine generated designs, compared to human created designs. Toward this end, 1187 participants were recruited via Amazon mechanical Turk (AMT) to analyze the perceived functional characteristics of both human created two-dimensional (2D) sketches and sketches generated by a deep learning generative model. In addition, a computer simulation was used to test the capability of the sketched ideas to perform their intended function and explore the validity of participants' responses. The results reveal that both participants and computer simulation evaluations were in agreement, indicating that sketches generated via the deep generative design model were more likely to perform their intended function, compared to human created sketches used to train the model. The results also reveal that participants were subject to biases while evaluating the sketches, and their age and domain knowledge were positively correlated with their perceived functionality of sketches. The results provide evidence that supports the capabilities of deep learning generative design tools to generate functional ideas and their potential to assist designers in creative tasks such as ideation.

Original languageEnglish (US)
Article number021104
JournalJournal of Mechanical Design, Transactions of the ASME
Volume141
Issue number2
DOIs
StatePublished - Feb 1 2019

Fingerprint

Computer simulation
Deep learning

All Science Journal Classification (ASJC) codes

  • Mechanics of Materials
  • Mechanical Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

@article{34092fff06cb43048dc4d9e39e27957d,
title = "Exploring biases between human and machine generated designs",
abstract = "The objective of this work is to explore the possible biases that individuals may have toward the perceived functionality of machine generated designs, compared to human created designs. Toward this end, 1187 participants were recruited via Amazon mechanical Turk (AMT) to analyze the perceived functional characteristics of both human created two-dimensional (2D) sketches and sketches generated by a deep learning generative model. In addition, a computer simulation was used to test the capability of the sketched ideas to perform their intended function and explore the validity of participants' responses. The results reveal that both participants and computer simulation evaluations were in agreement, indicating that sketches generated via the deep generative design model were more likely to perform their intended function, compared to human created sketches used to train the model. The results also reveal that participants were subject to biases while evaluating the sketches, and their age and domain knowledge were positively correlated with their perceived functionality of sketches. The results provide evidence that supports the capabilities of deep learning generative design tools to generate functional ideas and their potential to assist designers in creative tasks such as ideation.",
author = "Lopez, {Christian E.} and Miller, {Scarlett Rae} and Tucker, {Conrad S.}",
year = "2019",
month = "2",
day = "1",
doi = "10.1115/1.4041857",
language = "English (US)",
volume = "141",
journal = "Journal of Mechanical Design - Transactions of the ASME",
issn = "1050-0472",
publisher = "ASME",
number = "2",

}

Exploring biases between human and machine generated designs. / Lopez, Christian E.; Miller, Scarlett Rae; Tucker, Conrad S.

In: Journal of Mechanical Design, Transactions of the ASME, Vol. 141, No. 2, 021104, 01.02.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Exploring biases between human and machine generated designs

AU - Lopez, Christian E.

AU - Miller, Scarlett Rae

AU - Tucker, Conrad S.

PY - 2019/2/1

Y1 - 2019/2/1

N2 - The objective of this work is to explore the possible biases that individuals may have toward the perceived functionality of machine generated designs, compared to human created designs. Toward this end, 1187 participants were recruited via Amazon mechanical Turk (AMT) to analyze the perceived functional characteristics of both human created two-dimensional (2D) sketches and sketches generated by a deep learning generative model. In addition, a computer simulation was used to test the capability of the sketched ideas to perform their intended function and explore the validity of participants' responses. The results reveal that both participants and computer simulation evaluations were in agreement, indicating that sketches generated via the deep generative design model were more likely to perform their intended function, compared to human created sketches used to train the model. The results also reveal that participants were subject to biases while evaluating the sketches, and their age and domain knowledge were positively correlated with their perceived functionality of sketches. The results provide evidence that supports the capabilities of deep learning generative design tools to generate functional ideas and their potential to assist designers in creative tasks such as ideation.

AB - The objective of this work is to explore the possible biases that individuals may have toward the perceived functionality of machine generated designs, compared to human created designs. Toward this end, 1187 participants were recruited via Amazon mechanical Turk (AMT) to analyze the perceived functional characteristics of both human created two-dimensional (2D) sketches and sketches generated by a deep learning generative model. In addition, a computer simulation was used to test the capability of the sketched ideas to perform their intended function and explore the validity of participants' responses. The results reveal that both participants and computer simulation evaluations were in agreement, indicating that sketches generated via the deep generative design model were more likely to perform their intended function, compared to human created sketches used to train the model. The results also reveal that participants were subject to biases while evaluating the sketches, and their age and domain knowledge were positively correlated with their perceived functionality of sketches. The results provide evidence that supports the capabilities of deep learning generative design tools to generate functional ideas and their potential to assist designers in creative tasks such as ideation.

UR - http://www.scopus.com/inward/record.url?scp=85059069380&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059069380&partnerID=8YFLogxK

U2 - 10.1115/1.4041857

DO - 10.1115/1.4041857

M3 - Article

VL - 141

JO - Journal of Mechanical Design - Transactions of the ASME

JF - Journal of Mechanical Design - Transactions of the ASME

SN - 1050-0472

IS - 2

M1 - 021104

ER -