Hierarchical Feature Extraction for Efficient Design of Microfluidic Flow Patterns

Kin Gwn Lore, Daniel Stoecklein, Michael Davies, Baskar Ganapathysubramanian, Soumik Sarkar
Proceedings of the 1st International Workshop on Feature Extraction: Modern Questions and Challenges at NIPS 2015, PMLR 44:213-225, 2015.

Abstract

Deep neural networks are being widely used for feature representation learning in diverse problem areas ranging from object recognition and speech recognition to robotic perception and human disease prediction. We demonstrate a novel, perhaps the first application of deep learning in mechanical design, specifically to learn complex microfluidic flow patterns in order to solve inverse problems in fluid mechanics. A recent discovery showed the ability to control the fluid deformations in a microfluidic channel by placing a sequence of pillars. This provides a fundamental tool for numerous material science, manufacturing and biological applications. However, designing pillar sequences for user-defined deformations is practically infeasible as the current process requires laborious and time-consuming design iterations in a very large, highly nonlinear design space that can have as large as 10^15 possibilities. We demonstrate that hierarchical feature extraction can potentially lead to a scalable design tool via learning semantic representations from a relatively small number of flow pattern examples. The paper compares the performances of pre-trained deep neural networks and deep convolutional neural networks as well as their learnt features. We show that a balanced training data generation process with respect to a metric on the output space improves the feature extraction performance. Overall, the deep learning based design process is shown to expedite the current state-of-the-art design approaches by more than 600 times.

Cite this Paper

BibTeX
@InProceedings{pmlr-v44-lore15, title = {Hierarchical Feature Extraction for Efficient Design of Microfluidic Flow Patterns}, author = {Lore, Kin Gwn and Stoecklein, Daniel and Davies, Michael and Ganapathysubramanian, Baskar and Sarkar, Soumik}, booktitle = {Proceedings of the 1st International Workshop on Feature Extraction: Modern Questions and Challenges at NIPS 2015}, pages = {213--225}, year = {2015}, editor = {Storcheus, Dmitry and Rostamizadeh, Afshin and Kumar, Sanjiv}, volume = {44}, series = {Proceedings of Machine Learning Research}, address = {Montreal, Canada}, month = {11 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v44/lore15.pdf}, url = {https://proceedings.mlr.press/v44/lore15.html}, abstract = {Deep neural networks are being widely used for feature representation learning in diverse problem areas ranging from object recognition and speech recognition to robotic perception and human disease prediction. We demonstrate a novel, perhaps the first application of deep learning in mechanical design, specifically to learn complex microfluidic flow patterns in order to solve inverse problems in fluid mechanics. A recent discovery showed the ability to control the fluid deformations in a microfluidic channel by placing a sequence of pillars. This provides a fundamental tool for numerous material science, manufacturing and biological applications. However, designing pillar sequences for user-defined deformations is practically infeasible as the current process requires laborious and time-consuming design iterations in a very large, highly nonlinear design space that can have as large as 10^15 possibilities. We demonstrate that hierarchical feature extraction can potentially lead to a scalable design tool via learning semantic representations from a relatively small number of flow pattern examples. The paper compares the performances of pre-trained deep neural networks and deep convolutional neural networks as well as their learnt features. We show that a balanced training data generation process with respect to a metric on the output space improves the feature extraction performance. Overall, the deep learning based design process is shown to expedite the current state-of-the-art design approaches by more than 600 times.} }
Endnote
%0 Conference Paper %T Hierarchical Feature Extraction for Efficient Design of Microfluidic Flow Patterns %A Kin Gwn Lore %A Daniel Stoecklein %A Michael Davies %A Baskar Ganapathysubramanian %A Soumik Sarkar %B Proceedings of the 1st International Workshop on Feature Extraction: Modern Questions and Challenges at NIPS 2015 %C Proceedings of Machine Learning Research %D 2015 %E Dmitry Storcheus %E Afshin Rostamizadeh %E Sanjiv Kumar %F pmlr-v44-lore15 %I PMLR %P 213--225 %U https://proceedings.mlr.press/v44/lore15.html %V 44 %X Deep neural networks are being widely used for feature representation learning in diverse problem areas ranging from object recognition and speech recognition to robotic perception and human disease prediction. We demonstrate a novel, perhaps the first application of deep learning in mechanical design, specifically to learn complex microfluidic flow patterns in order to solve inverse problems in fluid mechanics. A recent discovery showed the ability to control the fluid deformations in a microfluidic channel by placing a sequence of pillars. This provides a fundamental tool for numerous material science, manufacturing and biological applications. However, designing pillar sequences for user-defined deformations is practically infeasible as the current process requires laborious and time-consuming design iterations in a very large, highly nonlinear design space that can have as large as 10^15 possibilities. We demonstrate that hierarchical feature extraction can potentially lead to a scalable design tool via learning semantic representations from a relatively small number of flow pattern examples. The paper compares the performances of pre-trained deep neural networks and deep convolutional neural networks as well as their learnt features. We show that a balanced training data generation process with respect to a metric on the output space improves the feature extraction performance. Overall, the deep learning based design process is shown to expedite the current state-of-the-art design approaches by more than 600 times.
RIS
TY - CPAPER TI - Hierarchical Feature Extraction for Efficient Design of Microfluidic Flow Patterns AU - Kin Gwn Lore AU - Daniel Stoecklein AU - Michael Davies AU - Baskar Ganapathysubramanian AU - Soumik Sarkar BT - Proceedings of the 1st International Workshop on Feature Extraction: Modern Questions and Challenges at NIPS 2015 DA - 2015/12/08 ED - Dmitry Storcheus ED - Afshin Rostamizadeh ED - Sanjiv Kumar ID - pmlr-v44-lore15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 44 SP - 213 EP - 225 L1 - http://proceedings.mlr.press/v44/lore15.pdf UR - https://proceedings.mlr.press/v44/lore15.html AB - Deep neural networks are being widely used for feature representation learning in diverse problem areas ranging from object recognition and speech recognition to robotic perception and human disease prediction. We demonstrate a novel, perhaps the first application of deep learning in mechanical design, specifically to learn complex microfluidic flow patterns in order to solve inverse problems in fluid mechanics. A recent discovery showed the ability to control the fluid deformations in a microfluidic channel by placing a sequence of pillars. This provides a fundamental tool for numerous material science, manufacturing and biological applications. However, designing pillar sequences for user-defined deformations is practically infeasible as the current process requires laborious and time-consuming design iterations in a very large, highly nonlinear design space that can have as large as 10^15 possibilities. We demonstrate that hierarchical feature extraction can potentially lead to a scalable design tool via learning semantic representations from a relatively small number of flow pattern examples. The paper compares the performances of pre-trained deep neural networks and deep convolutional neural networks as well as their learnt features. We show that a balanced training data generation process with respect to a metric on the output space improves the feature extraction performance. Overall, the deep learning based design process is shown to expedite the current state-of-the-art design approaches by more than 600 times. ER -
APA
Lore, K.G., Stoecklein, D., Davies, M., Ganapathysubramanian, B. & Sarkar, S.. (2015). Hierarchical Feature Extraction for Efficient Design of Microfluidic Flow Patterns. Proceedings of the 1st International Workshop on Feature Extraction: Modern Questions and Challenges at NIPS 2015, in Proceedings of Machine Learning Research 44:213-225 Available from https://proceedings.mlr.press/v44/lore15.html.

Related Material