Deep Convolutional Mixture Density Network for Inverse Design of Layered Photonic Structures
Ontology highlight
ABSTRACT:
SUBMITTER:
PROVIDER: S-EPMC10686261 | biostudies-literature | 2020 Sep
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Predicting physical response of an artificially structured material is of particular interest for scientific and engineering applications. Here we use deep learning to predict optical response of artificially engineered nanophotonic devices. In addition to predicting forward approximation of transmission response for any given topology, this approach allows us to inversely approximate designs for a targeted optical response. Our Deep Neural Network (DNN) could design compact (2.6 × 2.6 μm2) silicon-on-insulator (SOI)-based 1 × 2 power splitters with various target splitting ratios in a fraction of a second. This model is trained to minimize the reflection (to smaller than ~ -20 dB) while achieving maximum transmission efficiency above 90% and target splitting specifications. This approach paves the way for rapid design of integrated photonic components relying on complex nanostructures.
| S-EPMC6361971 | biostudies-literature
Project description:Deep learning (DL) has emerged as a promising tool for photonic inverse design. Nevertheless, despite the initial success in retrieving spectra of modest complexity with nearly instantaneous readout, DL-assisted design methods often underperform in accuracy compared with advanced optimization techniques and have not proven competitive in handling spectra of practical usefulness. Here, we introduce a tandem optimization model that combines a mixture density network (MDN) and a fully connected (FC) network to inversely design practical thin-film high reflectors. The multimodal nature of the MDN gives access to infinite candidate designs described by probability distributions, which are iteratively sampled and evaluated by the FC network to allow for rapid optimization. We show that the proposed model can retrieve the reflectance spectra of 20-layer thin-film structures. More interestingly, it reproduces with high precision the periodic structures of high reflectors derived from physical principles, even though no such information is included in the training data. Improved designs with extended high-reflectance zones are also demonstrated. Our approach combines the high-efficiency advantage of DL with the optimization-enabled performance improvement, enabling efficient and on-demand inverse design for practical applications.
| S-EPMC9651023 | biostudies-literature
Project description:The inverse design of photonic integrated circuits (PICs) presents distinctive computational challenges, including their large memory requirements. Advancements in the two-photon polymerization (2PP) fabrication process introduce additional complexity, necessitating the development of more flexible optimization algorithms to enable the creation of multimaterial 3D structures with unique properties. This paper presents a memory efficient reverse-mode automatic differentiation framework for finite-difference time-domain (FDTD) simulations that can handle complex constraints arising from novel fabrication methods. Our method is based on straight-through gradient estimation that enables nondifferentiable shape parametrizations. We demonstrate the effectiveness of our approach by creating increasingly complex structures to solve the coupling problems in PICs. The results highlight the potential of our method for future PIC design and practical applications.
| S-EPMC11822695 | biostudies-literature
Project description: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.
| S-EPMC11501320 | biostudies-literature
Project description:We introduce AtacWorks (https://github.com/clara-genomics/AtacWorks), a method to denoise and identify accessible chromatin regions from low-coverage or low-quality ATAC-seq data. AtacWorks uses a deep neural network to learn a mapping between noisy ATAC-seq data and corresponding higher-coverage or higher-quality data. We apply this approach to as few as 50 hematopoietic stem cells to identify regulatory elements that are differentially-accessible between rare lineage-primed cell subpopulations.
2021-01-11 | GSE147113 | GEO
Project description:Nasopharyngeal carcinoma (NPC) is one of the most common head and neck cancers. Early diagnosis plays a critical role in the treatment of NPC. To aid diagnosis, deep learning methods can provide interpretable clues for identifying NPC from magnetic resonance images (MRI). To identify the optimal models, we compared the discrimination performance of hierarchical and simple layered convolutional neural networks (CNN). Retrospectively, we collected the MRI images of patients and manually built the tailored NPC image dataset. We examined the performance of the representative CNN models including shallow CNN, ResNet50, ResNet101, and EfficientNet-B7. By fine-tuning, shallow CNN, ResNet50, ResNet101, and EfficientNet-B7 achieved the precision of 72.2%, 94.4%, 92.6%, and 88.4%, displaying the superiority of deep hierarchical neural networks. Among the examined models, ResNet50 with pre-trained weights demonstrated the best classification performance over other types of CNN with accuracy, precision, and an F1-score of 0.93, 0.94, and 0.93, respectively. The fine-tuned ResNet50 achieved the highest prediction performance and can be used as a potential tool for aiding the diagnosis of NPC tumors.
| S-EPMC9601165 | biostudies-literature
Project description:Recent advances in inverse-design approaches for discovering optical structures based on desired functional characteristics have reshaped the landscape of nanophotonic structures, where most studies have focused on how light interacts with nanophotonic structures only. When quantum emitters (QEs), such as atoms, molecules, and quantum dots, are introduced to couple to the nanophotonic structures, the light-matter interactions become much more complicated, forming a rapidly developing field - quantum nanophotonics. Typical quantum functional characteristics depend on the intrinsic properties of the QE and its electromagnetic environment created by the nanophotonic structures, commonly represented by a scalar quantity, local-density-of-states (LDOS). In this work, we introduce a generalized inverse-design framework in quantum nanophotonics by taking LDOS as the bridge to connect the nanophotonic structures and the quantum functional characteristics. We take a simple system consisting of QEs sitting on a single multilayer shell-metal-nanoparticle (SMNP) as an example, apply fully-connected neural networks to model the LDOS of SMNP, inversely design and optimize the geometry of the SMNP based on LDOS, and realize desirable quantum characteristics in two quantum nanophotonic problems: spontaneous emission and entanglement. Our work introduces deep learning to the quantum optics domain for advancing quantum device designs; and provides a new platform for practicing deep learning to design nanophotonic structures for complex problems without a direct link between structures and functional characteristics.
| S-EPMC11501149 | biostudies-literature
Project description:Plasmonic nanoantennas with suitable far-field characteristics are of huge interest for utilization in optical wireless links, inter-/intrachip communications, LiDARs, and photonic integrated circuits due to their exceptional modal confinement. Despite its success in shaping robust antenna design theories in radio frequency and millimeter-wave regimes, conventional transmission line theory finds its validity diminished in the optical frequencies, leading to a noticeable void in a generalized theory for antenna design in the optical domain. By utilizing neural networks, and through a one-time training of the network, one can transform the plasmonic nanoantennas design into an automated, data-driven task. In this work, we have developed a multi-head deep convolutional neural network serving as an efficient inverse-design framework for plasmonic patch nanoantennas. Our framework is designed with the main goal of determining the optimal geometries of nanoantennas to achieve the desired (inquired by the designer) S 11 and radiation pattern simultaneously. The proposed approach preserves the one-to-many mappings, enabling us to generate diverse designs. In addition, apart from the primary fabrication limitations that were considered while generating the dataset, further design and fabrication constraints can also be applied after the training process. In addition to possessing an exceptionally rapid surrogate solver capable of predicting S 11 and radiation patterns throughout the entire design frequency spectrum, we are introducing what we believe to be the pioneering inverse design network. This network enables the creation of efficient plasmonic antennas while concurrently accommodating customizable queries for both S 11 and radiation patterns, achieving remarkable accuracy within a single network framework. Our framework is capable of designing a wide range of devices, including single band, dual band, and broadband antennas, with directivities and radiation efficiencies reaching 11.07 dBi and 75 %, respectively, for a single patch. The proposed approach has been developed as a transformative shift in the inverse design of photonics components, with its impact extending beyond antenna design, opening a new paradigm toward real-time design of application-specific nanophotonic devices.
| S-EPMC11501072 | biostudies-literature
Project description:This research enhances crowd analysis by focusing on excessive crowd analysis and crowd density predictions for Hajj and Umrah pilgrimages. Crowd analysis usually analyzes the number of objects within an image or a frame in the videos and is regularly solved by estimating the density generated from the object location annotations. However, it suffers from low accuracy when the crowd is far away from the surveillance camera. This research proposes an approach to overcome the problem of estimating crowd density taken by a surveillance camera at a distance. The proposed approach employs a fully convolutional neural network (FCNN)-based method to monitor crowd analysis, especially for the classification of crowd density. This study aims to address the current technological challenges faced in video analysis in a scenario where the movement of large numbers of pilgrims with densities ranging between 7 and 8 per square meter. To address this challenge, this study aims to develop a new dataset based on the Hajj pilgrimage scenario. To validate the proposed method, the proposed model is compared with existing models using existing datasets. The proposed FCNN based method achieved a final accuracy of 100%, 98%, and 98.16% on the proposed dataset, the UCSD dataset, and the JHU-CROWD dataset, respectively. Additionally, The ResNet based method obtained final accuracy of 97%, 89%, and 97% for the proposed dataset, UCSD dataset, and JHU-CROWD dataset, respectively. The proposed Hajj-Crowd-2021 crowd analysis dataset and the model outperformed the other state-of-the-art datasets and models in most cases.
| S-EPMC9044363 | biostudies-literature
Project description:Cryo-electron microscopy (cryo-EM) has become a leading approach for protein structure determination, but it remains challenging to accurately model atomic structures with cryo-EM density maps. We propose a hybrid method, CR-I-TASSER (cryo-EM iterative threading assembly refinement), which integrates deep neural-network learning with I-TASSER assembly simulations for automated cryo-EM structure determination. The method is benchmarked on 778 proteins with simulated and experimental density maps, where CR-I-TASSER constructs models with a correct fold (template modeling (TM) score >0.5) for 643 targets that is 64% higher than the best of some other de novo and refinement-based approaches on high-resolution data samples. Detailed data analyses showed that the main advantage of CR-I-TASSER lies in the deep learning-based Cα position prediction, which significantly improves the threading template quality and therefore boosts the accuracy of final models through optimized fragment assembly simulations. These results demonstrate a new avenue to determine cryo-EM protein structures with high accuracy and robustness covering various target types and density map resolutions.
| S-EPMC8852347 | biostudies-literature