Journal articles: 'Deep Photonic Neural Networks'

1

Pai, Sunil, Zhanghao Sun, Tyler W. Hughes, Taewon Park, Ben Bartlett, Ian A. D. Williamson, Momchil Minkov, et al. "Experimentally realized in situ backpropagation for deep learning in photonic neural networks." Science 380, no. 6643 (April 28, 2023): 398–404. http://dx.doi.org/10.1126/science.ade8450.

Full text

Abstract:

Integrated photonic neural networks provide a promising platform for energy-efficient, high-throughput machine learning with extensive scientific and commercial applications. Photonic neural networks efficiently transform optically encoded inputs using Mach-Zehnder interferometer mesh networks interleaved with nonlinearities. We experimentally trained a three-layer, four-port silicon photonic neural network with programmable phase shifters and optical power monitoring to solve classification tasks using “in situ backpropagation,” a photonic analog of the most popular method to train conventional neural networks. We measured backpropagated gradients for phase-shifter voltages by interfering forward- and backward-propagating light and simulated in situ backpropagation for 64-port photonic neural networks trained on MNIST image recognition given errors. All experiments performed comparably to digital simulations ( > 94% test accuracy), and energy scaling analysis indicated a route to scalable machine learning.

APA, Harvard, Vancouver, ISO, and other styles

2

Sheng, Huayi. "Review of Integrated Diffractive Deep Neural Networks." Highlights in Science, Engineering and Technology 24 (December 27, 2022): 264–78. http://dx.doi.org/10.54097/hset.v24i.3957.

Full text

Abstract:

An integrated photonic diffractive deep neural network ( ID^2 NN) is one of the most exciting cross-discipline fields of artificial intelligence and optical computing, combining deep learning with the power of light-speed processing on an integrated platform. We know that neural network in a digital computer is based on transistors, which have significant challenges in keeping pace with Moore's law and limited real-time processing applications due to the increased computational costs associated with them. However, with remarkable progress and advancement in silicon photonic integrated circuits over the last few decades, ID^2 NN hold the promise of on-chip miniaturisation and high-speed performance with low power consumption. This paper covers the essential theoretical background for constructing the ID^2 NN and reviews the research status of optical diffractive neural networks in the field of neuromorphic computing. Problems of narrowing down current ID^2 NN applications are also included in this review. Finally, future research directions for ID^2 NN are discussed, and conclusions are delivered.

APA, Harvard, Vancouver, ISO, and other styles

3

Jiang, Jiaqi, and Jonathan A. Fan. "Multiobjective and categorical global optimization of photonic structures based on ResNet generative neural networks." Nanophotonics 10, no. 1 (September 22, 2020): 361–69. http://dx.doi.org/10.1515/nanoph-2020-0407.

Full text

Abstract:

AbstractWe show that deep generative neural networks, based on global optimization networks (GLOnets), can be configured to perform the multiobjective and categorical global optimization of photonic devices. A residual network scheme enables GLOnets to evolve from a deep architecture, which is required to properly search the full design space early in the optimization process, to a shallow network that generates a narrow distribution of globally optimal devices. As a proof-of-concept demonstration, we adapt our method to design thin-film stacks consisting of multiple material types. Benchmarks with known globally optimized antireflection structures indicate that GLOnets can find the global optimum with orders of magnitude faster speeds compared to conventional algorithms. We also demonstrate the utility of our method in complex design tasks with its application to incandescent light filters. These results indicate that advanced concepts in deep learning can push the capabilities of inverse design algorithms for photonics.

APA, Harvard, Vancouver, ISO, and other styles

4

Mao, Simei, Lirong Cheng, Caiyue Zhao, Faisal Nadeem Khan, Qian Li, and H. Y. Fu. "Inverse Design for Silicon Photonics: From Iterative Optimization Algorithms to Deep Neural Networks." Applied Sciences 11, no. 9 (April 23, 2021): 3822. http://dx.doi.org/10.3390/app11093822.

Full text

Abstract:

Silicon photonics is a low-cost and versatile platform for various applications. For design of silicon photonic devices, the light-material interaction within its complex subwavelength geometry is difficult to investigate analytically and therefore numerical simulations are majorly adopted. To make the design process more time-efficient and to improve the device performance to its physical limits, various methods have been proposed over the past few years to manipulate the geometries of silicon platform for specific applications. In this review paper, we summarize the design methodologies for silicon photonics including iterative optimization algorithms and deep neural networks. In case of iterative optimization methods, we discuss them in different scenarios in the sequence of increased degrees of freedom: empirical structure, QR-code like structure and irregular structure. We also review inverse design approaches assisted by deep neural networks, which generate multiple devices with similar structure much faster than iterative optimization methods and are thus suitable in situations where piles of optical components are needed. Finally, the applications of inverse design methodology in optical neural networks are also discussed. This review intends to provide the readers with the suggestion for the most suitable design methodology for a specific scenario.

APA, Harvard, Vancouver, ISO, and other styles

5

Dang, Dharanidhar, Sai Vineel Reddy Chittamuru, Sudeep Pasricha, Rabi Mahapatra, and Debashis Sahoo. "BPLight-CNN: A Photonics-Based Backpropagation Accelerator for Deep Learning." ACM Journal on Emerging Technologies in Computing Systems 17, no. 4 (October 31, 2021): 1–26. http://dx.doi.org/10.1145/3446212.

Full text

Abstract:

Training deep learning networks involves continuous weight updates across the various layers of the deep network while using a backpropagation (BP) algorithm. This results in expensive computation overheads during training. Consequently, most deep learning accelerators today employ pretrained weights and focus only on improving the design of the inference phase. The recent trend is to build a complete deep learning accelerator by incorporating the training module. Such efforts require an ultra-fast chip architecture for executing the BP algorithm. In this article, we propose a novel photonics-based backpropagation accelerator for high-performance deep learning training. We present the design for a convolutional neural network (CNN), BPLight-CNN , which incorporates the silicon photonics-based backpropagation accelerator. BPLight-CNN is a first-of-its-kind photonic and memristor-based CNN architecture for end-to-end training and prediction. We evaluate BPLight-CNN using a photonic CAD framework (IPKISS) on deep learning benchmark models, including LeNet and VGG-Net. The proposed design achieves (i) at least 34× speedup, 34× improvement in computational efficiency, and 38.5× energy savings during training; and (ii) 29× speedup, 31× improvement in computational efficiency, and 38.7× improvement in energy savings during inference compared with the state-of-the-art designs. All of these comparisons are done at a 16-bit resolution, and BPLight-CNN achieves these improvements at a cost of approximately 6% lower accuracy compared with the state-of-the-art.

APA, Harvard, Vancouver, ISO, and other styles

6

Ahmed, Moustafa, Yas Al-Hadeethi, Ahmed Bakry, Hamed Dalir, and Volker J. Sorger. "Integrated photonic FFT for photonic tensor operations towards efficient and high-speed neural networks." Nanophotonics 9, no. 13 (June 26, 2020): 4097–108. http://dx.doi.org/10.1515/nanoph-2020-0055.

Full text

Abstract:

AbstractThe technologically-relevant task of feature extraction from data performed in deep-learning systems is routinely accomplished as repeated fast Fourier transforms (FFT) electronically in prevalent domain-specific architectures such as in graphics processing units (GPU). However, electronics systems are limited with respect to power dissipation and delay, due to wire-charging challenges related to interconnect capacitance. Here we present a silicon photonics-based architecture for convolutional neural networks that harnesses the phase property of light to perform FFTs efficiently by executing the convolution as a multiplication in the Fourier-domain. The algorithmic executing time is determined by the time-of-flight of the signal through this photonic reconfigurable passive FFT ‘filter’ circuit and is on the order of 10’s of picosecond short. A sensitivity analysis shows that this optical processor must be thermally phase stabilized corresponding to a few degrees. Furthermore, we find that for a small sample number, the obtainable number of convolutions per {time, power, and chip area) outperforms GPUs by about two orders of magnitude. Lastly, we show that, conceptually, the optical FFT and convolution-processing performance is indeed directly linked to optoelectronic device-level, and improvements in plasmonics, metamaterials or nanophotonics are fueling next generation densely interconnected intelligent photonic circuits with relevance for edge-computing 5G networks by processing tensor operations optically.

APA, Harvard, Vancouver, ISO, and other styles

7

Sun, Yichen, Mingli Dong, Mingxin Yu, Jiabin Xia, Xu Zhang, Yuchen Bai, Lidan Lu, and Lianqing Zhu. "Nonlinear All-Optical Diffractive Deep Neural Network with 10.6 μm Wavelength for Image Classification." International Journal of Optics 2021 (February 27, 2021): 1–16. http://dx.doi.org/10.1155/2021/6667495.

Full text

Abstract:

A photonic artificial intelligence chip is based on an optical neural network (ONN), low power consumption, low delay, and strong antiinterference ability. The all-optical diffractive deep neural network has recently demonstrated its inference capabilities on the image classification task. However, the size of the physical model does not have miniaturization and integration, and the optical nonlinearity is not incorporated into the diffraction neural network. By introducing the nonlinear characteristics of the network, complex tasks can be completed with high accuracy. In this study, a nonlinear all-optical diffraction deep neural network (N-D2NN) model based on 10.6 μm wavelength is constructed by combining the ONN and complex-valued neural networks with the nonlinear activation function introduced into the structure. To be specific, the improved activation function of the rectified linear unit (ReLU), i.e., Leaky-ReLU, parametric ReLU (PReLU), and randomized ReLU (RReLU), is selected as the activation function of the N-D2NN model. Through numerical simulation, it is proved that the N-D2NN model based on 10.6 μm wavelength has excellent representation ability, which enables them to perform classification learning tasks of the MNIST handwritten digital dataset and Fashion-MNIST dataset well, respectively. The results show that the N-D2NN model with the RReLU activation function has the highest classification accuracy of 97.86% and 89.28%, respectively. These results provide a theoretical basis for the preparation of miniaturized and integrated N-D2NN model photonic artificial intelligence chips.

APA, Harvard, Vancouver, ISO, and other styles

8

Ren, Yangming, Lingxuan Zhang, Weiqiang Wang, Xinyu Wang, Yufang Lei, Yulong Xue, Xiaochen Sun, and Wenfu Zhang. "Genetic-algorithm-based deep neural networks for highly efficient photonic device design." Photonics Research 9, no. 6 (May 24, 2021): B247. http://dx.doi.org/10.1364/prj.416294.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Asano, Takashi, and Susumu Noda. "Iterative optimization of photonic crystal nanocavity designs by using deep neural networks." Nanophotonics 8, no. 12 (November 16, 2019): 2243–56. http://dx.doi.org/10.1515/nanoph-2019-0308.

Full text

Abstract:

AbstractDevices based on two-dimensional photonic-crystal nanocavities, which are defined by their air hole patterns, usually require a high quality (Q) factor to achieve high performance. We demonstrate 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. First, a dataset comprising randomly generated cavity structures and their first principles Q factors is prepared. Then a deep neural network is trained using the initial dataset to obtain a regression function that approximately predicts the Q factors from the structural parameters. Several candidates for higher Q factors are chosen by searching the parameter space using the regression function. After adding these new structures and their first principles Q factors to the training dataset, the above process is repeated. As an example, a standard silicon-based L3 cavity is optimized by this method. A cavity design with a high Q factor exceeding 11 million is found within 101 iteration steps and a total of 8070 cavity structures. This theoretical Q factor is more than twice the previously reported record values of the cavity designs detected by the evolutionary algorithm and the leaky mode visualization method. It is found that structures with higher Q factors can be detected within less iteration steps by exploring not only the parameter space near the present highest-Q structure but also that distant from the present dataset.

APA, Harvard, Vancouver, ISO, and other styles

10

Li, Renjie, Xiaozhe Gu, Yuanwen Shen, Ke Li, Zhen Li, and Zhaoyu Zhang. "Smart and Rapid Design of Nanophotonic Structures by an Adaptive and Regularized Deep Neural Network." Nanomaterials 12, no. 8 (April 16, 2022): 1372. http://dx.doi.org/10.3390/nano12081372.

Full text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

11

Shi, Bin, Nicola Calabretta, and Ripalta Stabile. "Numerical Simulation of an InP Photonic Integrated Cross-Connect for Deep Neural Networks on Chip." Applied Sciences 10, no. 2 (January 9, 2020): 474. http://dx.doi.org/10.3390/app10020474.

Full text

Abstract:

We propose a novel photonic accelerator architecture based on a broadcast-and-weight approach for a deep neural network through a photonic integrated cross-connect. The single neuron and the complete neural network operation are numerically simulated. The weight calibration and weighted addition are reproduced and demonstrated to behave as in the experimental measurements. A dynamic range higher than 25 dB is predicted, in line with the measurements. The weighted addition operation is also simulated and analyzed as a function of the optical crosstalk and the number of input colors involved. In particular, while an increase in optical crosstalk negatively influences the simulated error, a greater number of channels results in better performance. The iris flower classification problem is solved by implementing the weight matrix of a trained three-layer deep neural network. The performance of the corresponding photonic implementation is numerically investigated by tuning the optical crosstalk and waveguide loss, in order to anticipate energy consumption per operation. The analysis of the prediction error as a function of the optical crosstalk per layer suggests that the first layer is essential to the final accuracy. The ultimate accuracy shows a quasi-linear dependence between the prediction accuracy and the errors per layer for a normalized root mean square error lower than 0.09, suggesting that there is a maximum level of error permitted at the first layer for guaranteeing a final accuracy higher than 89%. However, it is still possible to find good local minima even for an error higher than 0.09, due to the stochastic nature of the network we are analyzing. Lower levels of path losses allow for half the power consumption at the matrix multiplication unit, for the same error level, offering opportunities for further improved performance. The good agreement between the simulations and the experiments offers a solid base for studying the scalability of this kind of network.

APA, Harvard, Vancouver, ISO, and other styles

12

Skontranis, Menelaos, George Sarantoglou, Stavros Deligiannidis, Adonis Bogris, and Charis Mesaritakis. "Time-Multiplexed Spiking Convolutional Neural Network Based on VCSELs for Unsupervised Image Classification." Applied Sciences 11, no. 4 (February 3, 2021): 1383. http://dx.doi.org/10.3390/app11041383.

Full text

Abstract:

In this work, we present numerical results concerning a multilayer “deep” photonic spiking convolutional neural network, arranged so as to tackle a 2D image classification task. The spiking neurons used are typical two-section quantum-well vertical-cavity surface-emitting lasers that exhibit isomorphic behavior to biological neurons, such as integrate-and-fire excitability and timing encoding. The isomorphism of the proposed scheme to biological networks is extended by replicating the retina ganglion cell for contrast detection in the photonic domain and by utilizing unsupervised spike dependent plasticity as the main training technique. Finally, in this work we also investigate the possibility of exploiting the fast carrier dynamics of lasers so as to time-multiplex spatial information and reduce the number of physical neurons used in the convolutional layers by orders of magnitude. This last feature unlocks new possibilities, where neuron count and processing speed can be interchanged so as to meet the constraints of different applications.

APA, Harvard, Vancouver, ISO, and other styles

13

Haffner, Christian, Andreas Joerg, Michael Doderer, Felix Mayor, Daniel Chelladurai, Yuriy Fedoryshyn, Cosmin Ioan Roman, et al. "Nano–opto-electro-mechanical switches operated at CMOS-level voltages." Science 366, no. 6467 (November 14, 2019): 860–64. http://dx.doi.org/10.1126/science.aay8645.

Full text

Abstract:

Combining reprogrammable optical networks with complementary metal-oxide semiconductor (CMOS) electronics is expected to provide a platform for technological developments in on-chip integrated optoelectronics. We demonstrate how opto-electro-mechanical effects in micrometer-scale hybrid photonic-plasmonic structures enable light switching under CMOS voltages and low optical losses (0.1 decibel). Rapid (for example, tens of nanoseconds) switching is achieved by an electrostatic, nanometer-scale perturbation of a thin, and thus low-mass, gold membrane that forms an air-gap hybrid photonic-plasmonic waveguide. Confinement of the plasmonic portion of the light to the variable-height air gap yields a strong opto-electro-mechanical effect, while photonic confinement of the rest of the light minimizes optical losses. The demonstrated hybrid architecture provides a route to develop applications for CMOS-integrated, reprogrammable optical systems such as optical neural networks for deep learning.

APA, Harvard, Vancouver, ISO, and other styles

14

Shi, Bin, Nicola Calabretta, and Ripalta Stabile. "Emulation and modelling of semiconductor optical amplifier-based all-optical photonic integrated deep neural network with arbitrary depth." Neuromorphic Computing and Engineering 2, no. 3 (September 1, 2022): 034010. http://dx.doi.org/10.1088/2634-4386/ac8827.

Full text

Abstract:

Abstract We experimentally demonstrate the emulation of scaling of the semiconductor optical amplifier (SOA) based integrated all-optical neural network in terms of number of input channels and layer cascade, with chromatic input at the neuron and monochromatic output conversion, obtained by exploiting cross-gain-modulation effect. We propose a noise model for investigating the signal degradation on the signal processing after cascades of SOAs, and we validate it via experimental results. Both experiments and simulations claim that the all-optical neuron (AON), with wavelength conversion as non-linear function, is able to compress noise for noisy optical inputs. This suggests that the use of SOA-based AON with wavelength conversion may allow for building neural networks with arbitrary depth. In fact, an arbitrarily deep neural network, built out of seven-channel input AONs, is shown to guarantee an error minor than 0.1 when operating at input power levels of −20 dBm/channel and with a 6 dB input dynamic range. Then the simulations results, extended to an arbitrary number of input channels and layers, suggest that by cascading and interconnecting multiple of these monolithically integrated AONs, it is possible to build a neural network with 12-inputs/neuron 12 neurons/layer and arbitrary depth scaling, or an 18-inputs/neuron 18-neurons/layer for single layer implementation, to maintain an output error <0.1. Further improvement in height scalability can be obtained by optimizing the input power.

APA, Harvard, Vancouver, ISO, and other styles

15

Chen, Xinyu, Renjie Li, Yueyao Yu, Yuanwen Shen, Wenye Li, Yin Zhang, and Zhaoyu Zhang. "POViT: Vision Transformer for Multi-Objective Design and Characterization of Photonic Crystal Nanocavities." Nanomaterials 12, no. 24 (December 9, 2022): 4401. http://dx.doi.org/10.3390/nano12244401.

Full text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

16

Hegde, Ravi S. "Photonics Inverse Design: Pairing Deep Neural Networks With Evolutionary Algorithms." IEEE Journal of Selected Topics in Quantum Electronics 26, no. 1 (January 2020): 1–8. http://dx.doi.org/10.1109/jstqe.2019.2933796.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Shi, Bin, Nicola Calabretta, and Ripalta Stabile. "Deep Neural Network Through an InP SOA-Based Photonic Integrated Cross-Connect." IEEE Journal of Selected Topics in Quantum Electronics 26, no. 1 (January 2020): 1–11. http://dx.doi.org/10.1109/jstqe.2019.2945548.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Head, Sarah, and Mehdi Keshavarz Hedayati. "Inverse Design of Distributed Bragg Reflectors Using Deep Learning." Applied Sciences 12, no. 10 (May 11, 2022): 4877. http://dx.doi.org/10.3390/app12104877.

Full text

Abstract:

Distributed Bragg Reflectors are optical structures capable of manipulating light behaviour, which are formed by stacking layers of thin-film materials. The inverse design of such structures is desirable, but not straightforward using conventional numerical methods. This study explores the application of Deep Learning to the design of a six-layer system, through the implementation of a Tandem Neural Network. The challenge is split into three sections: the generation of training data using the Transfer Matrix method, the design of a Simulation Neural Network (SNN) which maps structural geometry to spectral output, and finally an Inverse Design Neural Network (IDNN) which predicts the geometry required to produce target spectra. The latter enables the designer to develop custom multilayer systems with desired reflection properties. The SNN achieved an average accuracy of 97% across the dataset, with the IDNN achieving 94%. By using this inverse design method, custom-made reflectors can be manufactured in milliseconds, significantly reducing the cost of generating photonic devices and thin-film optics.

APA, Harvard, Vancouver, ISO, and other styles

19

Meng, Xiangyan, Nuannuan Shi, Guangyi Li, Wei Li, Ninghua Zhu, and Ming Li. "Optical Convolutional Neural Networks: Methodology and Advances (Invited)." Applied Sciences 13, no. 13 (June 26, 2023): 7523. http://dx.doi.org/10.3390/app13137523.

Full text

Abstract:

As a leading branch of deep learning, the convolutional neural network (CNN) is inspired by the natural visual perceptron mechanism of living things, showing great application in image recognition, language processing, and other fields. Photonics technology provides a new route for intelligent signal processing with the dramatic potential of its ultralarge bandwidth and ultralow power consumption, which automatically completes the computing process after the signal propagates through the processor with an analog computing architecture. In this paper, we focus on the key enabling technology of optical CNN, including reviewing the recent advances in the research hotspots, overviewing the current challenges and limitations that need to be further overcome, and discussing its potential application.

APA, Harvard, Vancouver, ISO, and other styles

20

Panusa, Giulia, Niyazi Ulas Dinc, and Demetri Psaltis. "Photonic waveguide bundles using 3D laser writing and deep neural network image reconstruction." Optics Express 30, no. 2 (January 11, 2022): 2564. http://dx.doi.org/10.1364/oe.446775.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Tu, Xin, Wansheng Xie, Zhenmin Chen, Ming-Feng Ge, Tianye Huang, Chaolong Song, and H. Y. Fu. "Analysis of Deep Neural Network Models for Inverse Design of Silicon Photonic Grating Coupler." Journal of Lightwave Technology 39, no. 9 (May 1, 2021): 2790–99. http://dx.doi.org/10.1109/jlt.2021.3057473.

Full text

APA, Harvard, Vancouver, ISO, and other styles

22

Alagappan, Gandhi, Jun Rong Ong, Zaifeng Yang, Thomas Yong Long Ang, Weijiang Zhao, Yang Jiang, Wenzu Zhang, and Ching Eng Png. "Leveraging AI in Photonics and Beyond." Photonics 9, no. 2 (January 28, 2022): 75. http://dx.doi.org/10.3390/photonics9020075.

Full text

Abstract:

Artificial intelligence (AI) techniques have been spreading in most scientific areas and have become a heated focus in photonics research in recent years. Forward modeling and inverse design using AI can achieve high efficiency and accuracy for photonics components. With AI-assisted electronic circuit design for photonics components, more advanced photonics applications have emerged. Photonics benefit a great deal from AI, and AI, in turn, benefits from photonics by carrying out AI algorithms, such as complicated deep neural networks using photonics components that use photons rather than electrons. Beyond the photonics domain, other related research areas or topics governed by Maxwell’s equations share remarkable similarities in using the help of AI. The studies in computational electromagnetics, the design of microwave devices, as well as their various applications greatly benefit from AI. This article reviews leveraging AI in photonics modeling, simulation, and inverse design; leveraging photonics computing for implementing AI algorithms; and leveraging AI beyond photonics topics, such as microwaves and quantum-related topics.

APA, Harvard, Vancouver, ISO, and other styles

23

Hamerly, Ryan. "The Future of Deep Learning Is Photonic: Reducing the energy needs of neural networks might require computing with light." IEEE Spectrum 58, no. 7 (July 2021): 30–47. http://dx.doi.org/10.1109/mspec.2021.9475393.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Li, Caiyun, Jiangyong He, Yange Liu, Yang Yue, Luhe Zhang, Longfei Zhu, Mengjie Zhou, Congcong Liu, Kaiyan Zhu, and Zhi Wang. "Comparing Performance of Deep Convolution Networks in Reconstructing Soliton Molecules Dynamics from Real-Time Spectral Interference." Photonics 8, no. 2 (February 13, 2021): 51. http://dx.doi.org/10.3390/photonics8020051.

Full text

Abstract:

Deep neural networks have enabled the reconstruction of optical soliton molecules with more complex structures using the real-time spectral interferences obtained by photonic time-stretch dispersive Fourier transformation (TS-DFT) technology. In this paper, we propose to use three kinds of deep convolution networks (DCNs), including VGG, ResNets, and DenseNets, for revealing internal dynamics evolution of soliton molecules based on the real-time spectral interferences. When analyzing soliton molecules with equidistant composite structures, all three models are effective. The DenseNets with layers of 48 perform the best for extracting the dynamic information of complex five-soliton molecules from TS-DFT data. The mean Pearson correlation coefficient (MPCC) between the predicted results and the real results is about 0.9975. Further, the ResNets in which the MPCC achieves 0.9906 also has the better ability of phase extraction than VGG which the MPCC is about 0.9739. The general applicability is demonstrated for extracting internal information from complex soliton molecule structures with high accuracy. The presented DCNs-based techniques can be employed to explore undiscovered mechanisms underlying the distribution and evolution of large numbers of solitons in dissipative systems in experimental research.

APA, Harvard, Vancouver, ISO, and other styles

25

Zhou, Yuewen, Fangzheng Zhang, Jingzhan Shi, and Shilong Pan. "Deep neural network-assisted high-accuracy microwave instantaneous frequency measurement with a photonic scanning receiver." Optics Letters 45, no. 11 (May 27, 2020): 3038. http://dx.doi.org/10.1364/ol.391883.

Full text

APA, Harvard, Vancouver, ISO, and other styles

26

Mirsu, Radu, Georgiana Simion, Catalin Daniel Caleanu, and Ioana Monica Pop-Calimanu. "A PointNet-Based Solution for 3D Hand Gesture Recognition." Sensors 20, no. 11 (June 5, 2020): 3226. http://dx.doi.org/10.3390/s20113226.

Full text

Abstract:

Gesture recognition is an intensively researched area for several reasons. One of the most important reasons is because of this technology’s numerous application in various domains (e.g., robotics, games, medicine, automotive, etc.) Additionally, the introduction of three-dimensional (3D) image acquisition techniques (e.g., stereovision, projected-light, time-of-flight, etc.) overcomes the limitations of traditional two-dimensional (2D) approaches. Combined with the larger availability of 3D sensors (e.g., Microsoft Kinect, Intel RealSense, photonic mixer device (PMD), CamCube, etc.), recent interest in this domain has sparked. Moreover, in many computer vision tasks, the traditional statistic top approaches were outperformed by deep neural network-based solutions. In view of these considerations, we proposed a deep neural network solution by employing PointNet architecture for the problem of hand gesture recognition using depth data produced by a time of flight (ToF) sensor. We created a custom hand gesture dataset, then proposed a multistage hand segmentation by designing filtering, clustering, and finding the hand in the volume of interest and hand-forearm segmentation. For comparison purpose, two equivalent datasets were tested: a 3D point cloud dataset and a 2D image dataset, both obtained from the same stream. Besides the advantages of the 3D technology, the accuracy of the 3D method using PointNet is proven to outperform the 2D method in all circumstances, even the 2D method that employs a deep neural network.

APA, Harvard, Vancouver, ISO, and other styles

27

Villegas Burgos, Carlos Mauricio, and Nickolas Vamivakas. "Challenges in the Path Toward a Scalable Silicon Photonics Implementation of Deep Neural Networks." IEEE Journal of Quantum Electronics 55, no. 5 (October 2019): 1–10. http://dx.doi.org/10.1109/jqe.2019.2934758.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Li, Fengrong, Yifan Sun, and XiangDong Zhang. "Deep-learning-based quantum imaging using NOON states." Journal of Physics Communications 6, no. 3 (March 1, 2022): 035005. http://dx.doi.org/10.1088/2399-6528/ac5e25.

Full text

Abstract:

Abstract The phase sensitivity of photonic NOON states scales O(1/N), which reaches the Heisenberg limit and indicates a great potential in high-quality optical phase sensing. However, the NOON states with large photon number N are experimentally difficult both to prepare and to operate. Such a fact severely limits their practical use. In this article, we soften the requirements for high-quality imaging based on NOON states with large N by introducing deep-learning methods. Specifically, we show that, with the help of deep-learning network, the fluctuation of the images obtained by the NOON states when N = 2 can be reduced to that of the currently infeasible imaging by the NOON states when N = 8. We numerically investigate our results obtained by two types of deep-learning models—deep neural network and convolutional denoising autoencoders, and characterize the imaging quality using the root mean square error. By comparison, we find that small-N NOON state imaging data is sufficient for training the deep-learning models of our schemes, which supports its direct application to the imaging processes.

APA, Harvard, Vancouver, ISO, and other styles

29

Yao, Kan, Rohit Unni, and Yuebing Zheng. "Intelligent nanophotonics: merging photonics and artificial intelligence at the nanoscale." Nanophotonics 8, no. 3 (January 25, 2019): 339–66. http://dx.doi.org/10.1515/nanoph-2018-0183.

Full text

Abstract:

AbstractNanophotonics has been an active research field over the past two decades, triggered by the rising interests in exploring new physics and technologies with light at the nanoscale. As the demands of performance and integration level keep increasing, the design and optimization of nanophotonic devices become computationally expensive and time-inefficient. Advanced computational methods and artificial intelligence, especially its subfield of machine learning, have led to revolutionary development in many applications, such as web searches, computer vision, and speech/image recognition. The complex models and algorithms help to exploit the enormous parameter space in a highly efficient way. In this review, we summarize the recent advances on the emerging field where nanophotonics and machine learning blend. We provide an overview of different computational methods, with the focus on deep learning, for the nanophotonic inverse design. The implementation of deep neural networks with photonic platforms is also discussed. This review aims at sketching an illustration of the nanophotonic design with machine learning and giving a perspective on the future tasks.

APA, Harvard, Vancouver, ISO, and other styles

30

Ai, Xiaocong, Shih-Chieh Hsu, Ke Li, and Chih-Ting Lu. "Probing highly collimated photon-jets with deep learning." Journal of Physics: Conference Series 2438, no. 1 (February 1, 2023): 012114. http://dx.doi.org/10.1088/1742-6596/2438/1/012114.

Full text

Abstract:

Abstract Many extensions of the standard model (SM) predict the existence of axion-like particles and/or dark Higgs in the sub-GeV scale. Two new sub-GeV particles, a scalar and a pseudoscalar, produced through the Higgs boson exotic decays, are investigated. The decay signatures of these two new particles with highly collimated photons in the final states are discriminated from the ones of SM backgrounds using the Convolutional Neural Networks and Boosted Decision Trees techniques. The sensitivities of searching for such new physics signatures at the Large Hadron Collider are obtained.

APA, Harvard, Vancouver, ISO, and other styles

31

Vlimant, Jean-Roch, Felice Pantaleo, Maurizio Pierini, Vladimir Loncar, Sofia Vallecorsa, Dustin Anderson, Thong Nguyen, and Alexander Zlokapa. "Large-Scale Distributed Training Applied to Generative Adversarial Networks for Calorimeter Simulation." EPJ Web of Conferences 214 (2019): 06025. http://dx.doi.org/10.1051/epjconf/201921406025.

Full text

Abstract:

In recent years, several studies have demonstrated the benefit of using deep learning to solve typical tasks related to high energy physics data taking and analysis. In particular, generative adversarial networks are a good candidate to supplement the simulation of the detector response in a collider environment. Training of neural network models has been made tractable with the improvement of optimization methods and the advent of GP-GPU well adapted to tackle the highly-parallelizable task of training neural nets. Despite these advancements, training of large models over large data sets can take days to weeks. Even more so, finding the best model architecture and settings can take many expensive trials. To get the best out of this new technology, it is important to scale up the available network-training resources and, consequently, to provide tools for optimal large-scale distributed training. In this context, our development of a new training workflow, which scales on multi-node/multi-GPU architectures with an eye to deployment on high performance computing machines is described. We describe the integration of hyper parameter optimization with a distributed training framework using Message Passing Interface, for models defined in keras [12] or pytorch [13]. We present results on the speedup of training generative adversarial networks trained on a data set composed of the energy deposition from electron, photons, charged and neutral hadrons in a fine grained digital calorimeter.

APA, Harvard, Vancouver, ISO, and other styles

32

Massari, Luca, Giulia Fransvea, Jessica D’Abbraccio, Mariangela Filosa, Giuseppe Terruso, Andrea Aliperta, Giacomo D’Alesio, et al. "Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin." Nature Machine Intelligence 4, no. 5 (May 2022): 425–35. http://dx.doi.org/10.1038/s42256-022-00487-3.

Full text

Abstract:

AbstractCollaborative robots are expected to physically interact with humans in daily living and the workplace, including industrial and healthcare settings. A key related enabling technology is tactile sensing, which currently requires addressing the outstanding scientific challenge to simultaneously detect contact location and intensity by means of soft conformable artificial skins adapting over large areas to the complex curved geometries of robot embodiments. In this work, the development of a large-area sensitive soft skin with a curved geometry is presented, allowing for robot total-body coverage through modular patches. The biomimetic skin consists of a soft polymeric matrix, resembling a human forearm, embedded with photonic fibre Bragg grating transducers, which partially mimics Ruffini mechanoreceptor functionality with diffuse, overlapping receptive fields. A convolutional neural network deep learning algorithm and a multigrid neuron integration process were implemented to decode the fibre Bragg grating sensor outputs for inference of contact force magnitude and localization through the skin surface. Results of 35 mN (interquartile range 56 mN) and 3.2 mm (interquartile range 2.3 mm) median errors were achieved for force and localization predictions, respectively. Demonstrations with an anthropomorphic arm pave the way towards artificial intelligence based integrated skins enabling safe human–robot cooperation via machine intelligence.

APA, Harvard, Vancouver, ISO, and other styles

33

Nakadai, Masahiro, Kengo Tanaka, Takashi Asano, Yasushi Takahashi, and Susumu Noda. "Statistical evaluation of Q factors of fabricated photonic crystal nanocavities designed by using a deep neural network." Applied Physics Express 13, no. 1 (December 3, 2019): 012002. http://dx.doi.org/10.7567/1882-0786/ab5978.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Zhao, Zeyu, Jie You, Jun Zhang, and Yuhua Tang. "Data-Enhanced Deep Greedy Optimization Algorithm for the On-Demand Inverse Design of TMDC-Cavity Heterojunctions." Nanomaterials 12, no. 17 (August 28, 2022): 2976. http://dx.doi.org/10.3390/nano12172976.

Full text

Abstract:

A data-enhanced deep greedy optimization (DEDGO) algorithm is proposed to achieve the efficient and on-demand inverse design of multiple transition metal dichalcogenides (TMDC)-photonic cavity-integrated heterojunctions operating in the strong coupling regime. Precisely, five types of photonic cavities with different geometrical parameters are employed to alter the optical properties of monolayer TMDC, aiming at discovering new and intriguing physics associated with the strong coupling effect. Notably, the traditional rigorous coupled wave analysis (RCWA) approach is utilized to generate a relatively small training dataset for the DEDGO algorithm. Importantly, one remarkable feature of DEDGO is the integration the decision theory of reinforcement learning, which remedies the deficiencies of previous research that focused more on modeling over decision making, increasing the success rate of inverse prediction. Specifically, an iterative optimization strategy, namely, deep greedy optimization, is implemented to improve the performance. In addition, a data enhancement method is also employed in DEDGO to address the dependence on a large amount of training data. The accuracy and effectiveness of the DEDGO algorithm are confirmed to be much higher than those of the random forest algorithm and deep neural network, making possible the replacement of the time-consuming conventional scanning optimization method with the DEDGO algorithm. This research thoroughly describes the universality, interpretability, and excellent performance of the DEDGO algorithm in exploring the underlying physics of TMDC-cavity heterojunctions, laying the foundations for the on-demand inverse design of low-dimensional material-based nano-devices.

APA, Harvard, Vancouver, ISO, and other styles

35

Gan, Linqiao, Fei Yu, Yazhou Wang, Ning Wang, Xinyue Zhu, Lili Hu, and Chunlei Yu. "Dispersion-Oriented Inverse Design of Photonic-Crystal Fiber for Four-Wave Mixing Application." Photonics 10, no. 3 (March 10, 2023): 294. http://dx.doi.org/10.3390/photonics10030294.

Full text

Abstract:

In this paper, we demonstrate the application of a deep learning neural network (DNN) in the dispersion-oriented inverse design of photonic-crystal fiber (PCF) for the fine-tuning of four-wave mixing (FWM). The empirical formula of PCF dispersion is applied instead of numerical simulation to generate a large dataset of phase-matching curves of various PCF designs, which significantly improves the accuracy of the DNN prediction. The accuracies of DNNs’ predicted PCF structure parameters are all above 95%. The simulations of the DNN-predicted PCFs structure demonstrate that the FWM wavelength has an average numerical mean square error (MAE) of 1.92 nm from the design target. With the help of DNN, we designed and fabricated a specific PCF for wavelength conversion via FWM from 1064 nm to 770 nm for biomedical imaging applications. Pumped by a microchip laser at 1064 nm, the signal wavelength is measured at 770.2 nm.

APA, Harvard, Vancouver, ISO, and other styles

36

Xie, Tangyao, and Jianguo Yu. "4Gbaud PS-16QAM D-Band Fiber-Wireless Transmission Over 4.6 km by Using Balance Complex-Valued NN Equalizer with Random Oversampling." Sensors 23, no. 7 (March 31, 2023): 3655. http://dx.doi.org/10.3390/s23073655.

Full text

Abstract:

D-band (110–170 GHz) is a promising direction for the future of 6th generation mobile networks (6G) for high-speed mobile communication since it has a large available bandwidth, and it can provide a peak rate of hundreds of Gbit/s. Compared with the traditional electrical approach, photonics millimeter wave (mm-wave) generation in D-band is more practical and effectively overcomes the bottleneck of electrical devices. However, long-distance D-band wireless transmission is still limited by some key factors such as large absorption loss and nonlinear noises. Deep neural network algorithms are regarded as an important technique to model the nonlinear wireless behavior, among which the study on complex-value equalization is critical, especially in coherent detection systems. Moreover, probabilistic shaping is useful to improve the transmission capacity but also causes an imbalanced machine learning issue. In this paper, we propose a novel complex-valued neural network equalizer coupled with balanced random oversampling (ROS). Thanks to the adaptive deep learning method for probabilistic shaping-quadrature amplitude modulation (PS-QAM), we successfully realize a 135 GHz 4Gbaud PS-16QAM with a shaping entropy of 3.56 bit/symbol wireless transmission over 4.6 km. The bit error ratio (BER) of 4Gbaud PS-16QAM can be decreased to a soft-decision forward error correction (SD-FEC) with a 25% overhead of 2×10−2. Therefore, we can achieve a net rate of an 11.4 Gbit/s D-band radio-over-fiber (ROF) delivery over 4.6 km air free wireless distance.

APA, Harvard, Vancouver, ISO, and other styles

37

Shinde, Ashwini, and Prof Madhav Ingle. "Hybrid Approach for Skin Disease Classification: Integrating Machine learning and Deep Learning." International Journal for Research in Applied Science and Engineering Technology 11, no. 5 (May 31, 2023): 3243–48. http://dx.doi.org/10.22214/ijraset.2023.52338.

Full text

Abstract:

Abstract: Skin infections are more common than many other diseases, and they can be caused by various factors such as infectious pollution, microorganisms, awareness, and infections. With the advancement of lasers and photonics-based medical technology, the diagnosis of skin infections has become faster and more accurate. However, the cost of such diagnosis is still limited and expensive. Therefore, image processing techniques are used to develop an automated assessment system for dermatology at an early stage. The extraction of features plays a crucial role in accurately and quickly diagnosing skin diseases. PC vision plays an important role in the detection of skin diseases in various ways. This study focuses on four skin diseases: ringworm, nail parasite, psoriasis, and atopic dermatitis. Convolutional neural networks have achieved close to or even better performance than humans in the imaging field. The skin diseases are classified using a machine learning algorithm, i.e., random forest, which achieves an accuracy of 98.23% after 100 epochs.

APA, Harvard, Vancouver, ISO, and other styles

38

Reddy, G. Mahesh, P. Hema Venkata Ramana, Ponnuru Anusha, Battula Kalyan Chakravarthy, Aravinda Kasukurthi, and Vaddempudi Sujatha Lakshmi. "A Survey on Sugarcane Leaf Disease Identification Using Deep Learning Technique(CNN)." International Journal on Recent and Innovation Trends in Computing and Communication 11, no. 5 (May 17, 2023): 248–54. http://dx.doi.org/10.17762/ijritcc.v11i5.6611.

Full text

Abstract:

The management of plant diseases is vital for the economical production of food and poses important challenges to the employment of soil, water, fuel and alternative inputs for agricultural functions. In each natural and cultivated populations, plants have inherent sickness tolerance, however there also are reports of devastating impacts of plant diseases. The management of diseases, however, within reason effective for many crops. sickness management is allotted through the employment of plants that square measure bred permanently resistance to several diseases and thru approaches to plant cultivation, like crop rotation, the employment of pathogen-free seeds, the given planting date and plant density, field wetness management, and therefore the use of pesticides. so as to enhance sickness management and to stay up with changes within the impact of diseases iatrogenic by the continued evolution and movement of plant pathogens and by changes in agricultural practices, continued progress within the science of soil science is required. Plant diseases cause tremendous economic losses for farmers globally. it's calculable that in additional developed settings across massive regions and lots of crop species, diseases usually cut back plant yields by ten percent per annum, however yield loss for diseases usually exceeds twenty percent in less developed settings. Around twenty-five percent of crop losses square measure caused by pests and diseases, the Food and Agriculture Organization estimates. to unravel this, new strategies for early detection of diseases and pests square measure required, like novel sensors that sight plant odours and spectrographic analysis and bio photonics that may diagnose plant health and metabolism. In artificial neural networks, deep learning is an element of a broader family of machine learning approaches supported realistic learning. Learning is often controlled, semi-supervised or unmonitored. to handle several real-world queries, Deep Learning Approaches are normally used. so as to differentiate pictures and acknowledge their options, coevolutionary neural networks have had a larger result. This article will do a Leaf Disease Identification Survey with Deep Learning Methods. It takes Sugarcane leaf as an instance to our paper.

APA, Harvard, Vancouver, ISO, and other styles

39

Valsecchi, Davide. "Deep learning techniques for energy clustering in the CMS ECAL." Journal of Physics: Conference Series 2438, no. 1 (February 1, 2023): 012077. http://dx.doi.org/10.1088/1742-6596/2438/1/012077.

Full text

Abstract:

Abstract The reconstruction of electrons and photons in CMS depends on topological clustering of the energy deposited by an incident particle in different crystals of the electromagnetic calorimeter (ECAL). These clusters are formed by aggregating neighbouring crystals according to the expected topology of an electromagnetic shower in the ECAL. The presence of upstream material (beampipe, tracker and support structures) causes electrons and photons to start showering before reaching the calorimeter. This effect, combined with the 3.8T CMS magnetic field, leads to energy being spread in several clusters around the primary one. It is essential to recover the energy contained in these satellite clusters in order to achieve the best possible energy resolution for physics analyses. Historically satellite clusters have been associated to the primary cluster using a purely topological algorithm which does not attempt to remove spurious energy deposits from additional pileup interactions (PU). The performance of this algorithm is expected to degrade during LHC Run 3 (2022+) because of the larger average PU levels and the increasing levels of noise due to the ageing of the ECAL detector. New methods are being investigated that exploit state-of-the-art deep learning architectures like Graph Neural Networks (GNN) and self-attention algorithms. These more sophisticated models improve the energy collection and are more resilient to PU and noise, helping to preserve the electron and photon energy resolution achieved during LHC Runs 1 and 2. This work will cover the challenges of training the models as well the opportunity that this new approach offers to unify the ECAL energy measurement with the particle identification steps used in the global CMS photon and electron reconstruction.

APA, Harvard, Vancouver, ISO, and other styles

40

Orban de Xivry, G., M. Quesnel, P.-O. Vanberg, O. Absil, and G. Louppe. "Focal plane wavefront sensing using machine learning: performance of convolutional neural networks compared to fundamental limits." Monthly Notices of the Royal Astronomical Society 505, no. 4 (June 9, 2021): 5702–13. http://dx.doi.org/10.1093/mnras/stab1634.

Full text

Abstract:

ABSTRACT Focal plane wavefront sensing (FPWFS) is appealing for several reasons. Notably, it offers high sensitivity and does not suffer from non-common path aberrations (NCPAs). The price to pay is a high computational burden and the need for diversity to lift any phase ambiguity. If those limitations can be overcome, FPWFS is a great solution for NCPA measurement, a key limitation for high-contrast imaging, and could be used as adaptive optics wavefront sensor. Here, we propose to use deep convolutional neural networks (CNNs) to measure NCPAs based on focal plane images. Two CNN architectures are considered: ResNet-50 and U-Net that are used, respectively, to estimate Zernike coefficients or directly the phase. The models are trained on labelled data sets and evaluated at various flux levels and for two spatial frequency contents (20 and 100 Zernike modes). In these idealized simulations, we demonstrate that the CNN-based models reach the photon noise limit in a large range of conditions. We show, for example, that the root mean squared wavefront error can be reduced to <λ/1500 for 2 × 106 photons in one iteration when estimating 20 Zernike modes. We also show that CNN-based models are sufficiently robust to varying signal-to-noise ratio, under the presence of higher order aberrations, and under different amplitudes of aberrations. Additionally, they display similar to superior performance compared to iterative phase retrieval algorithms. CNNs therefore represent a compelling way to implement FPWFS, which can leverage the high sensitivity of FPWFS over a broad range of conditions.

APA, Harvard, Vancouver, ISO, and other styles

41

Woods, Damien, and Thomas J. Naughton. "Photonic neural networks." Nature Physics 8, no. 4 (April 2012): 257–59. http://dx.doi.org/10.1038/nphys2283.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Brunner, Daniel, and Demetri Psaltis. "Competitive photonic neural networks." Nature Photonics 15, no. 5 (April 30, 2021): 323–24. http://dx.doi.org/10.1038/s41566-021-00803-0.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Yan, Ye-Peng, Guo-Jian Wang, Si-Yu Li, and Jun-Qing Xia. "Delensing of Cosmic Microwave Background Polarization with Machine Learning." Astrophysical Journal Supplement Series 267, no. 1 (June 27, 2023): 2. http://dx.doi.org/10.3847/1538-4365/acd2ce.

Full text

Abstract:

Abstract Primordial B-mode detection is one of the main goals of next-generation cosmic microwave background (CMB) experiments. Primordial B-modes are a unique signature of primordial gravitational waves (PGWs). However, the gravitational interaction of CMB photons with large-scale structures will distort the primordial E modes, adding a lensing B-mode component to the primordial B-mode signal. Removing the lensing effect (“delensing”) from observed CMB polarization maps will be necessary to improve the constraint of PGWs and obtain a primordial E-mode signal. Here, we introduce a deep convolutional neural network model named multi-input multi-output U-net (MIMO-UNet) to perform CMB delensing. The networks are trained on simulated CMB maps with size 20° × 20°. We first use MIMO-UNet to reconstruct the unlensing CMB polarization (Q and U) maps from observed CMB maps. The recovered E-mode power spectrum exhibits excellent agreement with the primordial EE power spectrum. The recovery of the primordial B-mode power spectrum for noise levels of 0, 1, and 2 μK-arcmin is greater than 98% at the angular scale of ℓ < 150. We additionally reconstruct the lensing B map from observed CMB maps. The recovery of the lensing B-mode power spectrum is greater than roughly 99% at the scales of ℓ > 200. We delens the observed B-mode power spectrum by subtracting the reconstructed lensing B-mode spectrum. The recovery of tensor B-mode power spectrum for noise levels of 0, 1, and 2 μK-arcmin is greater than 98% at the angular scales of ℓ < 120. Even at ℓ = 160, the recovery of tensor B-mode power spectrum is still around 71%.

APA, Harvard, Vancouver, ISO, and other styles

44

De Marinis, Lorenzo, Marco Cococcioni, Piero Castoldi, and Nicola Andriolli. "Photonic Neural Networks: A Survey." IEEE Access 7 (2019): 175827–41. http://dx.doi.org/10.1109/access.2019.2957245.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Sunny, Febin P., Ebadollah Taheri, Mahdi Nikdast, and Sudeep Pasricha. "A Survey on Silicon Photonics for Deep Learning." ACM Journal on Emerging Technologies in Computing Systems 17, no. 4 (June 30, 2021): 1–57. http://dx.doi.org/10.1145/3459009.

Full text

Abstract:

Deep learning has led to unprecedented successes in solving some very difficult problems in domains such as computer vision, natural language processing, and general pattern recognition. These achievements are the culmination of decades-long research into better training techniques and deeper neural network models, as well as improvements in hardware platforms that are used to train and execute the deep neural network models. Many application-specific integrated circuit (ASIC) hardware accelerators for deep learning have garnered interest in recent years due to their improved performance and energy-efficiency over conventional CPU and GPU architectures. However, these accelerators are constrained by fundamental bottlenecks due to (1) the slowdown in CMOS scaling, which has limited computational and performance-per-watt capabilities of emerging electronic processors; and (2) the use of metallic interconnects for data movement, which do not scale well and are a major cause of bandwidth, latency, and energy inefficiencies in almost every contemporary processor. Silicon photonics has emerged as a promising CMOS-compatible alternative to realize a new generation of deep learning accelerators that can use light for both communication and computation. This article surveys the landscape of silicon photonics to accelerate deep learning, with a coverage of developments across design abstractions in a bottom-up manner, to convey both the capabilities and limitations of the silicon photonics paradigm in the context of deep learning acceleration.

APA, Harvard, Vancouver, ISO, and other styles

46

Padilla-Zepeda, Efrain, Deni Torres-Roman, and Andres Mendez-Vazquez. "A Semantic Segmentation Framework for Hyperspectral Imagery Based on Tucker Decomposition and 3DCNN Tested with Simulated Noisy Scenarios." Remote Sensing 15, no. 5 (March 1, 2023): 1399. http://dx.doi.org/10.3390/rs15051399.

Full text

Abstract:

The present work, unlike others, does not try to reduce the noise in hyperspectral images to increase the semantic segmentation performance metrics; rather, we present a classification framework for noisy Hyperspectral Images (HSI), studying the classification performance metrics for different SNR levels and where the inputs are compressed. This framework consists of a 3D Convolutional Neural Network (3DCNN) that uses as input data a spectrally compressed version of the HSI, obtained from the Tucker Decomposition (TKD). The advantage of this classifier is the ability to handle spatial and spectral features from the core tensor, exploiting the spatial correlation of remotely sensed images of the earth surface. To test the performance of this framework, signal-independent thermal noise and signal-dependent photonic noise generators are implemented to simulate an extensive collection of tests, from 60 dB to −20 dB of Signal-to-Noise Ratio (SNR) over three datasets: Indian Pines (IP), University of Pavia (UP), and Salinas (SAL). For comparison purposes, we have included tests with Support Vector Machine (SVM), Random Forest (RF), 1DCNN, and 2DCNN. For the test cases, the datasets were compressed to only 40 tensor bands for a relative reconstruction error less than 1%. This framework allows us to classify the noisy data with better accuracy and significantly reduces the computational complexity of the Deep Learning (DL) model. The framework exhibits an excellent performance from 60 dB to 0 dB of SNR for 2DCNN and 3DCNN, achieving a Kappa coefficient from 0.90 to 1.0 in all the noisy data scenarios for a representative set of labeled samples of each class for training, from 5% to 10% for the datasets used in this work. The source code and log files of the experiments used for this paper are publicly available for research purposes.

APA, Harvard, Vancouver, ISO, and other styles

47

Sun, Miao, Shenglong Zhuo, and Patrick Yin Chiang. "Multi-Scale Histogram-Based Probabilistic Deep Neural Network for Super-Resolution 3D LiDAR Imaging." Sensors 23, no. 1 (December 30, 2022): 420. http://dx.doi.org/10.3390/s23010420.

Full text

Abstract:

LiDAR (Light Detection and Ranging) imaging based on SPAD (Single-Photon Avalanche Diode) technology suffers from severe area penalty for large on-chip histogram peak detection circuits required by the high precision of measured depth values. In this work, a probabilistic estimation-based super-resolution neural network for SPAD imaging that firstly uses temporal multi-scale histograms as inputs is proposed. To reduce the area and cost of on-chip histogram computation, only part of the histogram hardware for calculating the reflected photons is implemented on a chip. On account of the distribution rule of returned photons, a probabilistic encoder as a part of the network is first proposed to solve the depth estimation problem of SPADs. By jointly using this neural network with a super-resolution network, 16× up-sampling depth estimation is realized using 32 × 32 multi-scale histogram outputs. Finally, the effectiveness of this neural network was verified in the laboratory with a 32 × 32 SPAD sensor system.

APA, Harvard, Vancouver, ISO, and other styles

48

Stark, Pascal, Folkert Horst, Roger Dangel, Jonas Weiss, and Bert Jan Offrein. "Opportunities for integrated photonic neural networks." Nanophotonics 9, no. 13 (August 10, 2020): 4221–32. http://dx.doi.org/10.1515/nanoph-2020-0297.

Full text

Abstract:

AbstractPhotonics offers exciting opportunities for neuromorphic computing. This paper specifically reviews the prospects of integrated optical solutions for accelerating inference and training of artificial neural networks. Calculating the synaptic function, thereof, is computationally very expensive and does not scale well on state-of-the-art computing platforms. Analog signal processing, using linear and nonlinear properties of integrated optical devices, offers a path toward substantially improving performance and power efficiency of these artificial intelligence workloads. The ability of integrated photonics to operate at very high speeds opens opportunities for time-critical real-time applications, while chip-level integration paves the way to cost-effective manufacturing and assembly.

APA, Harvard, Vancouver, ISO, and other styles

49

Farhat, N. H. "Photonic neural networks and learning machines." IEEE Expert 7, no. 5 (October 1992): 63–72. http://dx.doi.org/10.1109/64.163674.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Demirkiran, Cansu, Furkan Eris, Gongyu Wang, Jonathan Elmhurst, Nick Moore, Nicholas C. Harris, Ayon Basumallik, Vijay Janapa Reddi, Ajay Joshi, and Darius Bunandar. "An Electro-Photonic System for Accelerating Deep Neural Networks." ACM Journal on Emerging Technologies in Computing Systems, July 12, 2023. http://dx.doi.org/10.1145/3606949.

Full text

Abstract:

The number of parameters in deep neural networks (DNNs) is scaling at about 5 × the rate of Moore’s Law. To sustain this growth, photonic computing is a promising avenue, as it enables higher throughput in dominant general matrix-matrix multiplication (GEMM) operations in DNNs than their electrical counterpart. However, purely photonic systems face several challenges including lack of photonic memory and accumulation of noise. In this paper, we present an electro-photonic accelerator, ADEPT, which leverages a photonic computing unit for performing GEMM operations, a vectorized digital electronic ASIC for performing non-GEMM operations, and SRAM arrays for storing DNN parameters and activations. In contrast to prior works in photonic DNN accelerators, we adopt a system-level perspective and show that the gains while large are tempered relative to prior expectations. Our goal is to encourage architects to explore photonic technology in a more pragmatic way considering the system as a whole to understand its general applicability in accelerating today’s DNNs. Our evaluation shows that ADEPT can provide, on average, 5.73 × higher throughput per Watt compared to the traditional systolic arrays (SAs) in a full-system, and at least 6.8 × and 2.5 × better throughput per Watt, compared to state-of-the-art electronic and photonic accelerators, respectively.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Deep Photonic Neural Networks'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles