POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices

  title={POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices},
  author={Xinyu Chen and Renjie Li and Yueyao Yu and Yuanwen Shen and Wenye Li and Zhaoyu Zhang and Yin Zhang},
We solve a fundamental challenge in semiconductor IC design: the fast and accurate characterization of nanoscale photonic devices. Much like the fusion between AI and EDA, many efforts have been made to apply DNNs such as convolutional neural networks (CNN) to prototype and characterize next-gen optoelectronic devices commonly found in photonic integrated circuits (PICs). These prior works generally strive to predict the quality factor ( Q ) and modal volume ( V ) of for instance, photonic… 


Smart and Rapid Design of Nanophotonic Structures by an Adaptive and Regularized Deep Neural Network
The proposed smart LRS-RCNN has been proven to greatly accelerate the design of photonic crystal structures as a state-of-the-art predictor for both Q-factor and V and can be modified and generalized to predict any type of optical properties for designing a wide range of different nanophotonic structures.
Deep learning-based modeling of photonic crystal nanocavities
The proposed approach overcomes shortcomings of existing methods and paves the way for DL-based on-demand and data-driven optimization of PC nanocavities applicable to the rapid design of nanoscale lasers and photonic integrated circuits.
Deep neural networks for the evaluation and design of photonic devices
This Review discusses how deep neural networks can serve as surrogate electromagnetic solvers, inverse modelling tools and global device optimizers, and how deep generative networks can learn geometric features in device distributions and even be configured to serve as robust global optimizers.
Deep learning in nano-photonics: inverse design and beyond
A critical review on the capabilities of deep learning for inverse design and the progress which has been made so far, and classify the different deep learning-based inverse design approaches at a higher level as well as by the context of their respective applications.
Optimization of photonic crystal nanocavities based on deep learning.
This approach can optimize 2D-PC structures over a parameter space of a size unfeasibly large for previous optimization methods that were based solely on direct calculations and is also useful for improving other optical characteristics.
Iterative optimization of photonic crystal nanocavity designs by using deep neural networks
It is demonstrated that hole patterns with very high Q factors can be efficiently found by the iteration procedure consisting of machine learning of the relation between the hole pattern and the corresponding Q factor and new dataset generation based on the regression function obtained by machine learning.
Mapping the design space of photonic topological states via deep learning.
A deep learning framework to map the design space of topological states in the photonic crystals and reconciles the dimension mismatch between the input (topological properties) and output (design parameters) vector spaces and the non-uniqueness that arises from one-to-many function mappings.
Deep learning for the design of photonic structures
Recent progress in deep-learning-based photonic design is reviewed by providing the historical background, algorithm fundamentals and key applications, with the emphasis on various model architectures for specific photonic tasks.
Designing integrated photonic devices using artificial neural networks.
A practical artificial neural network design framework for devices that can be used as building blocks in integrated photonic circuits and both forward and inverse design tools enabled by the ANN are developed and demonstrated.
CvT: Introducing Convolutions to Vision Transformers
A new architecture is presented that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both de-signs, and the positional encoding, a crucial component in existing Vision Transformers, can be safely re-moved in this model.