Abstract Photonics inverse design relies on human experts to search for a design topology that satisfies certain optical specifications with their experience and intuitions, which is relatively labor-intensive, slow, and sub-optimal. Machine learning has emerged as a powerful tool to automate this inverse design process. However, supervised or semi-supervised deep learning is unsuitable for this task due to: (1) a severe shortage of available training data due to the high computational complexity of physics-based simulations along with a lack of open-source datasets and/or the need for a pre-trained neural network model; (2) the issue of one-to-many mapping or non-unique solutions; and (3) the inability to perform optimization of the photonic structure beyond inverse designing. Reinforcement Learning (RL) has the potential to overcome the above three challenges. Here, we propose Learning to Design Optical-Resonators (L2DO) to leverage RL that learns to autonomously inverse design nanophotonic laser cavities without any prior knowledge while retrieving unique design solutions. L2DO incorporates two different algorithms – Deep Q-learning and Proximal Policy Optimization. We evaluate L2DO on two laser cavities: a long photonic crystal (PC) nanobeam and a PC nanobeam with an L3 cavity, both popular structures for semiconductor lasers. Trained for less than 152 hours on limited hardware resources, L2DO has improved state-of-the-art results in the literature by over 2 orders of magnitude and obtained 10 times better performance than a human expert working the same task for over a month. L2DO first learned to meet the required maxima of Q-factors (>50 million) and then proceeded to optimize some additional good-to-have features (e.g., resonance frequency, modal volume). Compared with iterative human designs and inverse design via supervised learning, L2DO can achieve over two orders of magnitude higher sample-efficiency without suffering from the three issues above. This work confirms the potential of deep RL algorithms to surpass human designs and marks a solid step towards a fully automated AI framework for photonics inverse design.

/pdf/deep-reinforcement-learning-empowers-automated-inverse-j8wcwiht.pdf

Deep reinforcement learning empowers automated inverse design and optimization of photonic crystals for nanoscale laser cavities

We study a new technique for solving the fundamental challenge in nanophotonic design: fast and accurate characterization of nanoscale photonic devices with minimal human intervention. Much like the fusion between Artificial Intelligence and Electronic Design Automation (EDA), many efforts have been made to apply deep neural networks (DNN) such as convolutional neural networks to prototype and characterize next-gen optoelectronic devices commonly found in Photonic Integrated Circuits. However, state-of-the-art DNN models are still far from being directly applicable in the real world: e.g., DNN-produced correlation coefficients between target and predicted physical quantities are about 80%, which is much lower than what it takes to generate reliable and reproducible nanophotonic designs. Recently, attention-based transformer models have attracted extensive interests and been widely used in Computer Vision and Natural Language Processing. In this work, we for the first time propose a Transformer model (POViT) to efficiently design and simulate photonic crystal nanocavities with multiple objectives under consideration. Unlike the standard Vision Transformer, our model takes photonic crystals as input data and changes the activation layer from GELU to an absolute-value function. Extensive experiments show that POViT significantly improves results reported by previous models: correlation coefficients are increased by over 12% (i.e., to 92.0%) and prediction errors are reduced by an order of magnitude, among several key metric improvements. Our work has the potential to drive the expansion of EDA to fully automated photonic design (i.e., PDA). The complete dataset and code will be released to promote research in the interdisciplinary field of materials science/physics and computer science.

/pdf/povit-vision-transformer-for-multi-objective-design-and-12nyglqg.pdf

POViT: Vision Transformer for Multi-Objective Design and Characterization of Photonic Crystal Nanocavities

End-to-end Text-to-speech (TTS) system can greatly improve the quality of synthesised speech. But it usually suffers form high time latency due to its auto-regressive structure. And the synthesised speech may also suffer from some error modes, e.g. repeated words, mispronunciations, and skipped words. In this paper, we propose a novel non-autoregressive, fully parallel end-to-end TTS system (FPETS). It utilizes a new alignment model and the recently proposed U-shape convolutional structure, UFANS. Different from RNN, UFANS can capture long term information in a fully parallel manner. Trainable position encoding and two-step training strategy are used for learning better alignments. Experimental results show FPETS utilizes the power of parallel computation and reaches a significant speed up of inference compared with state-of-the-art end-to-end TTS systems. More specifically, FPETS is 600X faster than Tacotron2, 50X faster than DCTTS and 10X faster than Deep Voice3. And FPETS can generates audios with equal or better quality and fewer errors comparing with other system. As far as we know, FPETS is the first end-to-end TTS system which is fully parallel.

pdf/fpets-fully-parallel-end-to-end-text-to-speech-system-40jv6pxu0y.pdf

FPETS : Fully Parallel End-to-End Text-to-Speech System

Deep learning techniques face the problem of overfitting due to their complex layer structure. Regularization methods are used to overcome this problem and improve the designed models. In this article, we use the combination of L1 regularization, L2 regularization, Elastic Net-regularization, and Dropout methods. The designed deep model using combination of these methods is considered with different rates. The deep network model using a combination of these methods is designed with different rates. Finally, the performance of all combination methods is compared with the Convolutional Neural Network model which does not use regularization methods. Experiments are performed using the Gold price per ounce data set and linear simulation model. The obtained results show that the performance of the combination model of Dropout and Elastic Net regularization is better than the other models. 

Combining Regularization and Dropout Techniques for Deep Convolutional Neural Network

/pdf/fpets-fully-parallel-end-to-end-text-to-speech-system-3wqnpetgss.pdf

FPETS: Fully Parallel End-to-End Text-to-Speech System

The design of nanophotonic structures based on deep learning is emerging rapidly in the research community. Design methods using Deep Neural Networks (DNN) are outperforming conventional physics-based simulations performed iteratively by human experts. Here, a self-adaptive and regularized DNN based on Convolutional Neural Networks (CNNs) for the smart and fast characterization of nanophotonic structures in high-dimensional design parameter space is presented. This proposed CNN model, named LRS-RCNN, utilizes dynamic learning rate scheduling and L2 regularization techniques to overcome overfitting and speed up training convergence and is shown to surpass the performance of all previous algorithms, with the exception of two metrics where it achieves a comparable level relative to prior works. We applied the model to two challenging types of photonic structures: 2D photonic crystals (e.g., L3 nanocavity) and 1D photonic crystals (e.g., nanobeam) and results show that LRS-RCNN achieves record-high prediction accuracies, strong generalizibility, and substantially faster convergence speed compared to prior works. Although still a proof-of-concept model, 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. It can also be modified and generalized to predict any type of optical properties for designing a wide range of different nanophotonic structures. The complete dataset and code will be released to aid the development of related research endeavors.

/pdf/smart-and-rapid-design-of-nanophotonic-structures-by-an-35w7zq8f.pdf

Smart and Rapid Design of Nanophotonic Structures by an Adaptive and Regularized Deep Neural Network

Neural networks with Auto-regressive structures, such as Recurrent Neural Networks (RNNs), have become the most appealing structures for acoustic modeling of parametric text to speech synthesis (TTS) in ecent studies. Despite the prominent capacity to capture long-term dependency, these models consist of massive sequential computations that cannot be fully parallel. In this paper, we propose a U-shaped Fully-parallel Acoustic Neural Structure (UFANS), which is a deconvolutional alternative of RNNs for Statistical Parametric Speech Synthesis (SPSS). The experiments verify that our proposed model is over 20 times faster than RNN based acoustic model, both training and inference on GPU with comparable speech quality. Furthermore, We also investigate that how long information dependence really matters to synthesized speech quality.

UFANS: U-shaped Fully-Parallel Acoustic Neural Structure For Statistical Parametric Speech Synthesis With 20X Faster.

Neural networks with auto-regressive structures, such as Recurrent Neural Network (RNN), have become the most appealing structures for acoustic model in parametric text-to-speech synthesis (TTS). Despite the prominent ability to generate high quality results, high inference cost of RNN model prevents its usage in industry TTS applications and services. In this paper, we propose a fully-parallel convolutional neural network based acoustic model, U-shaped Fully-parallel Acoustic Neural Structure (UFANS). Experiments show our model achieves 20 times speed up in inference and is 300 times faster than real time with comparable speech quality, which is suitable for industrial level TTS services.

UFANS: U-Shaped Fully-Parallel Acoustic Neural Structure for Statistical Parametric Speech Synthesis

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Zhen Li

Author Tools

Chat about Author

Papers

Smart and Rapid Design of Nanophotonic Structures by an Adaptive and Regularized Deep Neural Network

UFANS: U-shaped Fully-Parallel Acoustic Neural Structure For Statistical Parametric Speech Synthesis With 20X Faster.

UFANS: U-Shaped Fully-Parallel Acoustic Neural Structure for Statistical Parametric Speech Synthesis