A Reinforcement learning method for Optical Thin-Film Design

• URL: http://arxiv.org/abs/2102.09398v1
• Date: Sat, 13 Feb 2021 07:42:15 GMT
• Title: A Reinforcement learning method for Optical Thin-Film Design
• Authors: Anqing Jiang, Liangyao Chen, Osamu Yoshie
• Abstract summary: Machine learning is changing the methods associated with optical thin-film inverse design. We propose a new end-to-end algorithm for optical thin-film inverse design. We show how one can use this technique to optimize the spectra of a multi-layer solar absorber device.
• Score: 2.9005223064604078
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design. The vast majority of this research has focused on the parameter optimization (layer thickness, and structure size) of optical thin-films. A challenging problem that arises is an automated material search. In this work, we propose a new end-to-end algorithm for optical thin-film inverse design. This method combines the ability of unsupervised learning, reinforcement learning(RL) and includes a genetic algorithm to design an optical thin-film without any human intervention. Furthermore, with several concrete examples, we have shown how one can use this technique to optimize the spectra of a multi-layer solar absorber device.

Related papers

• Deep Learning Methods for Calibrated Photometric Stereo and Beyond [86.57469194387264]
  Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues. Deep learning methods have shown a powerful ability in the context of photometric stereo against non-Lambertian surfaces.
  arXiv  Detail & Related papers  (2022-12-16T11:27:44Z)
• EllipsoNet: Deep-learning-enabled optical ellipsometry for complex thin films [7.687090333084554]
  We propose a computational ellipsometry approach based on a conventional tabletop optical microscope and a deep learning model called EllipsoNet. Without any prior knowledge about the multilayer substrates, EllipsoNet can predict the complex refractive indices of thin films on top of these nontrivial substrates from experimentally measured optical reflectance spectra with high accuracies.
  arXiv  Detail & Related papers  (2022-10-11T17:18:09Z)
• Investigation of inverse design of multilayer thin-films with conditional invertible Neural Networks [62.997667081978825]
  We use conditional Invertible Neural Networks (cINNs) to inversely design multilayer thin-films given an optical target. We show that cINNs can generate proposals for thin-film configurations that are reasonably close to the desired target depending on random variables.
  arXiv  Detail & Related papers  (2022-10-10T12:29:20Z)
• Data driven design of optical resonators [0.0]
  In my thesis, I use Deep Learning for the inverse design of the Fabry-P'erot resonator. This system can be described fully analytically and is therefore ideal to study.
  arXiv  Detail & Related papers  (2021-12-21T16:44:13Z)
• TMM-Fast: A Transfer Matrix Computation Package for Multilayer Thin-Film Optimization [62.997667081978825]
  An advanced thin-film structure can consist of multiple materials with different thicknesses and numerous layers. Design and optimization of complex thin-film structures with multiple variables is a computationally heavy problem that is still under active research. We propose the Python package TMM-Fast which enables parallelized computation of reflection and transmission of light at different angles of incidence and wavelengths through the multilayer thin-film.
  arXiv  Detail & Related papers  (2021-11-24T14:47:37Z)
• Photonic Differential Privacy with Direct Feedback Alignment [66.61196212740359]
  We show how to leverage the intrinsic noise of optical random projections to build a differentially private DFA mechanism. We conduct experiments demonstrating the ability of our learning procedure to achieve solid end-task performance.
  arXiv  Detail & Related papers  (2021-06-07T14:18:01Z)
• Efficient and Differentiable Shadow Computation for Inverse Problems [64.70468076488419]
  Differentiable geometric computation has received increasing interest for image-based inverse problems. We propose an efficient yet efficient approach for differentiable visibility and soft shadow computation. As our formulation is differentiable, it can be used to solve inverse problems such as texture, illumination, rigid pose, and deformation recovery from images.
  arXiv  Detail & Related papers  (2021-04-01T09:29:05Z)
• Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces [103.08512487830669]
  This paper presents an uncalibrated deep neural network framework for the photometric stereo problem. Existing neural network-based methods either require exact light directions or ground-truth surface normals of the object or both. We propose an uncalibrated neural inverse rendering approach to this problem.
  arXiv  Detail & Related papers  (2020-12-12T10:33:08Z)
• Parameterized Reinforcement Learning for Optical System Optimization [0.0]
  A multi-layer optical system with designated optical characteristics is designed by several discrete and continuous parameters. Most methods merely determine the optimal thicknesses of the system's layers. We propose a method that considers the stacking of consecutive layers as parameterized actions in a Markov decision process.
  arXiv  Detail & Related papers  (2020-10-09T10:53:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.