Research Papers: Design Theory and Methodology

Design Manifolds Capture the Intrinsic Complexity and Dimension of Design Spaces

[+] Author and Article Information
Wei Chen

Department of Mechanical Engineering,
University of Maryland,
College Park, MD 20742
e-mail: wchen459@umd.edu

Mark Fuge

Department of Mechanical Engineering,
University of Maryland,
College Park, MD 20742
e-mail: fuge@umd.edu

Jonah Chazan

Department of Computer Science,
University of Maryland,
College Park, MD 20742
e-mail: jchazan@umd.edu

1Corresponding author.

Contributed by the Design Theory and Methodology Committee of ASME for publication in the JOURNAL OF MECHANICAL DESIGN. Manuscript received September 16, 2016; final manuscript received February 7, 2017; published online March 23, 2017. Assoc. Editor: Harrison M. Kim.

J. Mech. Des 139(5), 051102 (Mar 23, 2017) (10 pages) Paper No: MD-16-1647; doi: 10.1115/1.4036134 History: Received September 16, 2016; Revised February 07, 2017

This paper shows how to measure the intrinsic complexity and dimensionality of a design space. It assumes that high-dimensional design parameters actually lie in a much lower-dimensional space that represents semantic attributes—a design manifold. Past work has shown how to embed designs using techniques like autoencoders; in contrast, the method proposed in this paper first captures the inherent properties of a design space and then chooses appropriate embeddings based on the captured properties. We demonstrate this with both synthetic shapes of controllable complexity (using a generalization of the ellipse called the superformula) and real-world designs (glassware and airfoils). We evaluate multiple embeddings by measuring shape reconstruction error, pairwise distance preservation, and captured semantic attributes. By generating fundamental knowledge about the inherent complexity of a design space and how designs differ from one another, our approach allows us to improve design optimization, consumer preference learning, geometric modeling, and other design applications that rely on navigating complex design spaces. Ultimately, this deepens our understanding of design complexity in general.

Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.


Gielis, J. , 2003, “ A Generic Geometric Transformation That Unifies a Wide Range of Natural and Abstract Shapes,” Am. J. Bot., 90(3), pp. 333–338. [CrossRef] [PubMed]
Xu, K. , Kim, V. G. , Huang, Q. , Mitra, N. , and Kalogerakis, E. , 2016, “ Data-Driven Shape Analysis and Processing,” SIGGRAPH ASIA 2016 Courses, (SA), Macau, Dec. 5–8, pp. 1–4.
Müller, P. , Wonka, P. , Haegler, S. , Ulmer, A. , and Van Gool, L. , 2006, “ Procedural Modeling of Buildings,” ACM Trans. Graphics, 25(3), pp. 614–623. [CrossRef]
Talton, J. O. , Lou, Y. , Lesser, S. , Duke, J. , Měch, R. , and Koltun, V. , 2011, “ Metropolis Procedural Modeling,” ACM Trans. Graphics, 30(2), pp. 1–14. [CrossRef]
Cagan, J. , Campbell, M. I. , Finger, S. , and Tomiyama, T. , 2005, “ A Framework for Computational Design Synthesis: Model and Applications,” ASME J. Comput. Inf. Sci. Eng., 5(3), pp. 171–181. [CrossRef]
Wyatt, D. F. , Wynn, D. C. , Jarrett, J. P. , and Clarkson, P. J. , 2012, “ Supporting Product Architecture Design Using Computational Design Synthesis With Network Structure Constraints,” Res. Eng. Des., 23(1), pp. 17–52. [CrossRef]
Königseder, C. , and Shea, K. , 2015, “ Analyzing Generative Design Grammars,” Design Computing and Cognition'14, Springer, Cham, Switzerland, pp. 363–381.
Oberhauser, M. , Sartorius, S. , Gmeiner, T. , and Shea, K. , 2015, “ Computational Design Synthesis of Aircraft Configurations With Shape Grammars,” Design Computing and Cognition’14, Springer, Cham, Switzerland, pp. 21–39.
Königseder, C. , and Shea, K. , 2016, “ Comparing Strategies for Topologic and Parametric Rule Application in Automated Computational Design Synthesis,” ASME J. Mech. Des., 138(1), p. 011102. [CrossRef]
Chaudhuri, S. , and Koltun, V. , 2010, “ Data-Driven Suggestions for Creativity Support in 3D Modeling,” ACM Trans. Graphics, 29(6), pp. 1–10. [CrossRef]
Chaudhuri, S. , Kalogerakis, E. , Guibas, L. , and Koltun, V. , 2011, “ Probabilistic Reasoning for Assembly-Based 3D Modeling,” ACM Trans. Graphics, 30(4), pp. 1–10. [CrossRef]
Kalogerakis, E. , Chaudhuri, S. , Koller, D. , and Koltun, V. , 2012, “ A Probabilistic Model for Component-Based Shape Synthesis,” ACM Trans. Graphics, 31(4), pp. 1–11. [CrossRef]
Chaudhuri, S. , Kalogerakis, E. , Giguere, S. , and Funkhouser, T. , 2013, “ Attribit: Content Creation With Semantic Attributes,” 26th Annual ACM Symposium on User Interface Software and Technology (UIST), St. Andrews, Scotland, Oct. 8–11, pp. 193–202.
Guo, X. , Lin, J. , Xu, K. , and Jin, X. , 2014, “ Creature Grammar for Creative Modeling of 3D Monsters,” Graphical Models, 76(5), pp. 376–389. [CrossRef]
Talton, J. O. , Gibson, D. , Yang, L. , Hanrahan, P. , and Koltun, V. , 2009, “ Exploratory Modeling With Collaborative Design Spaces,” ACM Trans. Graphics, 28(5), pp. 1–10. [CrossRef]
Fish, N. , Averkiou, M. , Van Kaick, O. , Sorkine-Hornung, O. , Cohen-Or, D. , and Mitra, N. J. , 2014, “ Meta-Representation of Shape Families,” ACM Trans. Graphics, 33(4), pp. 1–11. [CrossRef]
Averkiou, M. , Kim, V. G. , Zheng, Y. , and Mitra, N. J. , 2014, “ Shapesynth: Parameterizing Model Collections for Coupled Shape Exploration and Synthesis,” Comput. Graphics Forum, 33(2), pp. 125–134. [CrossRef]
Yumer, M. E. , Asente, P. , Mech, R. , and Kara, L. B. , 2015, “ Procedural Modeling Using Autoencoder Networks,” 28th ACM User Interface Software and Technology Symposium (UIST), Daegu, Kyungpook, Korea, Nov. 8–11, pp. 109–118.
Burnap, A. , Liu, Y. , Pan, Y. , Lee, H. , Gonzalez, R. , and Papalambros, P. Y. , 2016, “ Estimating and Exploring the Product From Design Space Using Deep Generative Models,” ASME Paper No. DETC2016-60091.
Yumer, M. E. , Chaudhuri, S. , Hodgins, J. K. , and Kara, L. B. , 2015, “ Semantic Shape Editing Using Deformation Handles,” ACM Trans. Graphics, 34(4), pp. 1–12. [CrossRef]
Van der Maaten, L. , Postma, E. , and Van den Herik, H. , 2009, “ Dimensionality Reduction: A Comparative Review,” Technical Report No. TiCC TR 2009-005.
Bengio, Y. , Courville, A. , and Vincent, P. , 2013, “ Representation Learning: A Review and New Perspectives,” IEEE Trans. Pattern Anal. Mach. Intell., 35(8), pp. 1798–1828. [CrossRef] [PubMed]
Duvenaud, D. K. , Rippel, O. , Adams, R. P. , and Ghahramani, Z. , 2014, “ Avoiding Pathologies in Very Deep Networks,” arXiv:1402.5836.
Larsen, K. G. , and Nelson, J. , 2014, “ The Johnson–Lindenstrauss Lemma Is Optimal for Linear Dimensionality Reduction,” preprint arXiv:1411.2404.
Bartal, Y. , Recht, B. , and Schulman, L. J. , 2011, “ Dimensionality Reduction: Beyond the Johnson–Lindenstrauss Bound,” Twenty-Second Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), San Francisco, CA, Jan. 23–25, pp. 868–887.
Shawe-Taylor, J. , Williams, C. K. , Cristianini, N. , and Kandola, J. , 2005, “ On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA,” IEEE Trans. Inf. Theory, 51(7), pp. 2510–2522. [CrossRef]
Ng, A. Y. , Jordan, M. I. , and Weiss, Y. , 2001, “ On Spectral Clustering: Analysis and an Algorithm,” Advances in Neural Information Processing Systems, MIT Press, Cambridge, MA, Vol. 14, pp. 849–856.
Gong, D. , Zhao, X. , and Medioni, G. , 2012, “ Robust Multiple Manifolds Structure Learning,” preprint arXiv:1206.4624.
Zhang, Z. , Wang, J. , and Zha, H. , 2012, “ Adaptive Manifold Learning,” IEEE Trans. Pattern Anal. Mach. Intell., 34(2), pp. 253–265. [CrossRef] [PubMed]
Zelnik-Manor, L. , and Perona, P. , 2004, “ Self-Tuning Spectral Clustering,” Advances in Neural Information Processing Systems, MIT Press, Cambridge, MA, Vol. 17, pp. 1601–1608.
Samko, O. , Marshall, A. D. , and Rosin, P. L. , 2006, “ Selection of the Optimal Parameter Value for the Isomap Algorithm,” Pattern Recog. Lett., 27(9), pp. 968–979. [CrossRef]
Schölkopf, B. , Smola, A. , and Müller, K.-R. , 1998, “ Nonlinear Component Analysis as a Kernel Eigenvalue Problem,” Neural Comput., 10(5), pp. 1299–1319. [CrossRef]
Vincent, P. , Larochelle, H. , Lajoie, I. , Bengio, Y. , and Manzagol, P.-A. , 2010, “ Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network With a Local Denoising Criterion,” J. Mach. Learn. Res., 11(2), pp. 3371–3408.
Schölkopf, B. , Smola, A. , and Müller, K.-R. , 1997, “ Kernel Principal Component Analysis,” International Conference on Artificial Neural Networks (ICANN), Lausanne, Switzerland, Oct. 8–10, pp. 583–588.
Vincent, P. , Larochelle, H. , Bengio, Y. , and Manzagol, P.-A. , 2008, “ Extracting and Composing Robust Features With Denoising Autoencoders,” 25th International Conference on Machine Learning (ICML), Helsinki, Finland, July 5–9, pp. 1096–1103.
Bengio, Y. , Lamblin, P. , Popovici, D. , and Larochelle, H. , 2007, “ Greedy Layer-Wise Training of Deep Networks,” Advances in Neural Information Processing Systems (NIPS), MIT Press, Cambridge, MA, Vol. 19, pp. 153–160.
Hutter, F. , Hoos, H. H. , and Leyton-Brown, K. , 2011, “ Sequential Model-Based Optimization for General Algorithm Configuration,” Lecture Notes in Computer Science (LNCS), Vol. 6683, Springer, Berlin, pp. 507–523.
Makridakis, S. , 1993, “ Accuracy Measures: Theoretical and Practical Concerns,” Int. J. Forecasting, 9(4), pp. 527–529. [CrossRef]
Chen, W. , Chazan, J. , and Fuge, M. , 2016, “ How Designs Differ: Non-Linear Embeddings Illuminate Intrinsic Design Complexity,” ASME Paper No. DETC2016-60112.


Grahic Jump Location
Fig. 1

Three-dimensional visualization of high-dimensional design space showing that design parameters actually lie on a two-dimensional manifold

Grahic Jump Location
Fig. 2

Examples of superformula shapes

Grahic Jump Location
Fig. 3

Three-dimensional visualization of the superformula design space created by a linear mapping from the high-dimensional design space X to a three-dimensional space, solely for visualization. Each point represents a design. (a) Lineardesign space (d = 1) varying s, (b) nonlinear space (d = 2) varying s and n3, and (c) design space with multiple shape categories.

Grahic Jump Location
Fig. 4

Set boundary of the feasible semantic space: (a) create a convex hull of the training set in the semantic space, (b) copy the boundary of the convex hull to the grid of new designs generated from the semantic space, and (c) remove designs outside the boundary

Grahic Jump Location
Fig. 5

Illustration of pairwise distance preservation. Similar designs (A and B) have similar shape representations in X, thus are closer in X than dissimilar designs (A and C). We want such relation of pairwise distances to be preserved in F (i.e., dAB < dAC) such that shapes will vary in the same manner as they do in X.

Grahic Jump Location
Fig. 6

An example comparing shapes generated from the semantic space F versus the superformula parameter space P. If the embedding precisely captures the principal attributes, shapes from F should look like those from P—with neither extra unexpected shape variation nor missing diversity. (a) Shapes in the superformula parameter space and (b) generated shapes in the semantic space.

Grahic Jump Location
Fig. 7

Multiple superformula categories with intersection. Our approach correctly separates the three submanifolds, even though they all connect via a common seam. (a) Shapes in the superformula parameter space, (b) result of manifold clustering (as in Fig. 3, the design space X is visualized in three dimensions), and (c) generated shapes in semantic spaces. Since there are three categories, we have three separated semantic spaces.

Grahic Jump Location
Fig. 8

Multiple superformula categories with intersection and different intrinsic dimensions. Our intrinsic dimension estimator automatically detects the appropriate dimensionality of the semantic space for each design category (c). (a) Shapes in the superformula parameter space, (b) result of manifold clustering (as in Fig. 3, the design space X is visualized in three dimensions), and (c) generated shapes in semantic spaces.

Grahic Jump Location
Fig. 9

Synthesized glassware shapes in a 3D semantic space. The embedding captured three shape attributes—the rim diameter, the stem diameter, and the curvature.

Grahic Jump Location
Fig. 10

Synthesized airfoil shapes in a 3D semantic space. The embedding captured three shape attributes—the upper and lower surface protrusion and the trailing edge direction.

Grahic Jump Location
Fig. 11

Point A has high sample density and thus higher confidence that synthesized shapes will look similar to nearby real-world samples. In contrast, point B has low sample density and thus lower confidence but higher chance of generating an unusual or creative shape. Shade darkness correlates with higher local density. (a) Arrangement of training samples in the semantic space (for simplicity, this is a 2D projection of the 3D semantic space) and (b) synthesized shapes.

Grahic Jump Location
Fig. 12

Comparison of different embedding methods. The abnormal shapes generated by PCA and SdA are due to high reconstruction error and high GDI, respectively. (a) Shapes in the superformula parameter space, (b) reconstruction error and geodesic distance inconsistency, (c) embedding and shape synthesis result by PCA, (d) embedding and shape synthesis result by kernel PCA, and (e) embedding and shape synthesis result by a stacked denoising autoencoder.




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In