Deep neural network (DNN) surrogate models for the accelerated design of optical devices and systems: moving beyond fully-connected feed forward architectures

Ravi S. Hegde

doi:10.1117/12.2528380

9 September 2019 Deep neural network (DNN) surrogate models for the accelerated design of optical devices and systems: moving beyond fully-connected feed forward architectures

Ravi S. Hegde

Author Affiliations +

Proceedings Volume 11105, Novel Optical Systems, Methods, and Applications XXII; 1110508 (2019) https://doi.org/10.1117/12.2528380
Event: SPIE Optical Engineering + Applications, 2019, San Diego, California, United States

Abstract

Recently, we have proposed the pairing of Deep Neural Networks and evolutionary algorithms as a versatile route for the optimal design of optical devices and systems.¹ Here, we extend that work and investigate the use of deep Convolutional Neural Networks (CNN) as opposed to fully connected feedforward architectures. We show that networks built with convolutional layers, batch normalization (BN), parametric REctified Linear Unit (ReLU) and residual blocks achieve drastic reduction in parameter weights and training epochs in comparison to dense, fully-connected networks for comparable accuracy. The proposed lightweight CNNs when used for approximate objective evaluation in concert with DE global optimization resulted in nearly 8x speedup in convergence time. The choice of a network architecture and optimization of its hyperparameters is a tedious task and it is hoped that the systematic hyperparameter search reported here would assist others in faster model selection.

Conference Presentation

Citation Download Citation

Ravi S. Hegde "Deep neural network (DNN) surrogate models for the accelerated design of optical devices and systems: moving beyond fully-connected feed forward architectures", Proc. SPIE 11105, Novel Optical Systems, Methods, and Applications XXII, 1110508 (9 September 2019); https://doi.org/10.1117/12.2528380

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available