TY - JOUR
T1 - New roles for machine learning in design
AU - Reich, Yoram
AU - Konda, Suresh L.
AU - Levy, Sean N.
AU - Monarch, Ira A.
AU - Subrahmanian, Eswaran
N1 - Funding Information:
This research has been supported in part by the Engineering Design Research Center, a National Science Foundation Engineering Research Center. We would like to thank Robin King for comments on an earlier draft, to Steven Meyer and Steven Fenves for allowing us access to their study protocols, and to the reviewers for their constructive comments.
PY - 1993
Y1 - 1993
N2 - Research on machine learning in design has concentrated on the use and development of techniques that can solve simple well-defined problems. Invariably, this effort, while important at the early stages of the development of the field, cannot scale up to address real design problems since all existing techniques are based on simplifying assumptions that do not hold for real design. In particular, they do not address the dependence on context and multiple, often conflicting, interests that are constitutive of design. This paper analyzes the present situation and criticises a number of prevailing views. Subsequently, the paper offers an alternative approach whose goal is to advance the use of machine learning in design practice. The approach is partially integrated into a modeling system called n-dim. The use of machine learning in n-dim is presented and open research issues are outlined.
AB - Research on machine learning in design has concentrated on the use and development of techniques that can solve simple well-defined problems. Invariably, this effort, while important at the early stages of the development of the field, cannot scale up to address real design problems since all existing techniques are based on simplifying assumptions that do not hold for real design. In particular, they do not address the dependence on context and multiple, often conflicting, interests that are constitutive of design. This paper analyzes the present situation and criticises a number of prevailing views. Subsequently, the paper offers an alternative approach whose goal is to advance the use of machine learning in design practice. The approach is partially integrated into a modeling system called n-dim. The use of machine learning in n-dim is presented and open research issues are outlined.
KW - computational models
KW - design
KW - design practice
KW - flexible modeling
KW - machine learning
KW - multistrategy learning
KW - natural language processing
KW - shared memory
UR - https://www.scopus.com/pages/publications/0027887769
U2 - 10.1016/0954-1810(93)90003-X
DO - 10.1016/0954-1810(93)90003-X
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:0027887769
SN - 0954-1810
VL - 8
SP - 165
EP - 181
JO - Artificial Intelligence in Engineering
JF - Artificial Intelligence in Engineering
IS - 3
ER -