Coercing machine learning to output physically accurate results
Abstract/Contents
- Abstract
- Many machine/deep learning artificial neural networks are trained to simply be interpolation functions that map input variables to output values interpolated from the training data in a linear/nonlinear fashion. Even when the input/output pairs of the training data are physically accurate (e.g. the results of an experiment or numerical simulation), interpolated quantities can deviate quite far from being physically accurate. Although one could project the output of a network into a physically feasible region, such a postprocess is not captured by the energy function minimized when training the network; thus, the final projected result could incorrectly deviate quite far from the training data. We propose folding any such projection or postprocess directly into the network so that the final result is correctly compared to the training data by the energy function. Although we propose a general approach, we illustrate its efficacy on a specific convolutional neural network that takes in human pose parameters (joint rotations) and outputs a prediction of vertex positions representing a triangulated cloth mesh. While the original network outputs vertex positions with erroneously high stretching and compression energies, the new network trained with our physics "prior" remedies these issues producing highly improved results. We apply our physical postprocess in several applications to further demonstrate its effectiveness and robustness.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2020; ©2020 |
Publication date | 2020; 2020 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Geng, Zhenglin |
---|---|
Degree supervisor | Fedkiw, Ronald P, 1968- |
Thesis advisor | Fedkiw, Ronald P, 1968- |
Thesis advisor | Liu, Cheng-Yun Karen, 1977- |
Thesis advisor | Wu, Jiajun |
Degree committee member | Liu, Cheng-Yun Karen, 1977- |
Degree committee member | Wu, Jiajun |
Associated with | Stanford University, Computer Science Department |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Zhenglin Geng. |
---|---|
Note | Submitted to the Computer Science Department. |
Thesis | Thesis Ph.D. Stanford University 2020. |
Location | electronic resource |
Access conditions
- Copyright
- © 2020 by Zhenglin Geng
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...