Ms. Andy G. Varner Profile

Andy G. Varner

SPIE Involvement:

Author

Publications (6)

Proceedings Article | 7 June 2024 Presentation + Paper

Addressing multi-scale challenges in metasurface design with differentiable far-field propagation

Marshall Lindsay, Scott Kovaleski, Andy Varner, Charlie Veal, Derek Anderson, Stanton Price, Steven Price

Proceedings Volume 13042, 1304205 (2024) https://doi.org/10.1117/12.3013490

KEYWORDS: Wave propagation, Holograms, Wavefronts, Design, Imaging systems, Fourier optics, Aliasing

Read Abstract +

Proceedings Article | 7 June 2024 Presentation + Paper

Time-series neural networks to predict electromagnetic wave propagation

Andy Varner, Scott Kovaleski, Charlie Veal, Marshall Lindsay, Junyoung Shin, Derek Anderson, Stanton Price, Steven Price

Proceedings Volume 13042, 1304206 (2024) https://doi.org/10.1117/12.3013488

KEYWORDS: Wave propagation, Machine learning, Neural networks, Simulations, Near field optics, Electric fields

Read Abstract +

Proceedings Article | 7 June 2024 Presentation + Paper

Cooperative optimization of neural-network-based diffraction simulations and benchtop spatial light modulators

Marshall Lindsay, Scott Kovaleski, Andy Varner, Charlie Veal, Derek Anderson, Stanton Price, Steven Price

Proceedings Volume 13042, 1304207 (2024) https://doi.org/10.1117/12.3013482

KEYWORDS: Simulations, Holograms, Spatial light modulators, Wavefronts, Modulation, Device simulation

Read Abstract +

Proceedings Article | 7 June 2024 Presentation + Paper

Generalized comparison assessment of unstructured data using foundation model features

Charlie Veal, Marshall Lindsay, Andy Varner, Scott Kovaleski, Derek Anderson, Stanton Price, Steven Price

Proceedings Volume 13040, 1304008 (2024) https://doi.org/10.1117/12.3013836

KEYWORDS: Computer vision technology, Object detection

Read Abstract +

Proceedings Article | 14 June 2023 Presentation + Paper

Mapping meta-atoms to near field response for inverse design of optical metasurfaces

Andy Varner, Marshall Lindsay, Charlie Veal, Scott Kovaleski, Derek Anderson, Stanton Price, Steven Price

Proceedings Volume 12530, 125300J (2023) https://doi.org/10.1117/12.2661887

KEYWORDS: Electric fields, Machine learning, Design and modelling, Image restoration, Simulations, Near field, Near field optics

Read Abstract +

Proceedings Article | 14 June 2023 Presentation + Paper

Impact of data variety on physics-informed neural network lens design

Marshall Lindsay, Scott Kovaleski, Andy Varner, Charlie Veal, Justice Weber, Derek Anderson, Stanton Price, Steven Price

Proceedings Volume 12530, 125300B (2023) https://doi.org/10.1117/12.2661856

KEYWORDS: Neural networks, Wave propagation, Data modeling, Wavefronts, Modulation, Overfitting, Mathematical optimization, Lens design

Read Abstract +

The adoption of neural networks for optical component design has increased rapidly in recent years. In this design framework, the numerical simulation of optical wave propagation and material wave modulation are encoded directly as layers of a neural network. This direct encoding enables the optimization of physical quantities (e.g., the transmissivity values of the diffractive optical elements) by gradient descent and the backpropagation algorithm. For the body of work which uses these networks for simulation and optimization, there is a tendency to treat the training process as identical to traditional deep neural networks. However, to the best of our knowledge, there is yet an explicit evaluation of training parameters to support this intuition. This work aims to help fill this gap by providing an exploration and evaluation of data variety to help accelerate those in the community who wish to use this emerging design framework.The application of neural networks in optical component design has witnessed rapid growth in recent years. This design framework encodes the numerical simulation of optical wave propagation and material wave modulation directly within neural network layers, enabling the optimization of physical quantities, such as transmissivity values of diffractive optical elements, through gradient descent and backpropagation algorithms. Physics-informed neural networks have been employed in designing diffractive deep neural networks, optimizing holograms for near-eye displays and creating multi-objective traditional optics. However, there remains a lack of evaluation for training parameters, and discrete sampling considerations are often overlooked. To address these gaps, this study examines the impact of dataset variety on physics-informed neural networks in optimizing lenses that either satisfy or violate the Nyquist sampling criteria. Results show that increased data variety enhances optimized lens performance across all cases. Optimized lenses demonstrate improved imaging performance by reducing diffraction orders present in aliased analytical lenses. Moreover, we reveal that low data variety leads to overfit lenses that function as selective imagers, providing valuable insights for future lens design and optimization.

Showing 5 of 6 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years