ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

LSTM-based autoencoder for the inverse design of achromatic metalenses

Pillai, P and Rai, B and Yelashetty, A and Gupta, TD and Pal, P (2023) LSTM-based autoencoder for the inverse design of achromatic metalenses. In: AI and Optical Data Sciences IV 2023, 30 Jan - 2 Feb 2023, San Francisco.

Full text not available from this repository.
Official URL: https://doi.org/10.1117/12.2649737


We describe an LSAT-based auto encoder for inversely designing an achromatic meta lens comprised of cylindrical unit cells. The training data for our model has phase and transmission values corresponding to the heights and radii of each meta-unit. We use multiple data sequences (phase and transmission) to train the model and a multi-output model framework. The auto encoder is trained for 2500 iterations using the Adam optimizer with a learning rate of 0.001 and is subsequently used for inversely predicting the meta-unit dimensions at each radial position of the lens. Our model is validated via simulations as well as experiments.

Item Type: Conference Paper
Publication: Proceedings of SPIE - The International Society for Optical Engineering
Publisher: SPIE
Additional Information: The copyright for this article belongs to SPIE
Keywords: Computer vision; Long short-term memory; Transmissions, Auto encoders; Data sequences; Inverse designs; Inverse modelling; LSTM; MetaLens; Multiple data; Training data; Transmission value; Unit cells, Learning systems
Department/Centre: Division of Physical & Mathematical Sciences > Instrumentation Appiled Physics
Date Deposited: 15 Jun 2023 09:34
Last Modified: 15 Jun 2023 09:34
URI: https://eprints.iisc.ac.in/id/eprint/82043

Actions (login required)

View Item View Item