Design Target Achievement Index: A Differentiable Metric to Enhance Deep Generative Models in Multi-Objective Inverse Design
<jats:title>Abstract</jats:title> <jats:p>Deep Generative Machine Learning Models have been growing in popularity across the design community thanks to their ability to learn and mimic complex data distributions. While early works are promising, further advancement...
Main Authors: | Regenwetter, Lyle, Ahmed, Faez |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Mechanical Engineering |
Format: | Article |
Language: | English |
Published: |
American Society of Mechanical Engineers
2023
|
Online Access: | https://hdl.handle.net/1721.1/150668 |
Similar Items
-
Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design
by: Regenwetter, Lyle, et al.
Published: (2023) -
Deep Generative Models in Engineering Design: A Review
by: Regenwetter, Lyle, et al.
Published: (2023) -
Data-Driven Bicycle Design using Performance-Aware Deep Generative Models
by: Regenwetter, Lyle
Published: (2022) -
BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks
by: Regenwetter, Lyle, et al.
Published: (2023) -
FRAMED: An AutoML Approach for Structural Performance Prediction of Bicycle Frames
by: Regenwetter, Lyle, et al.
Published: (2023)