Temat: optical neural network

Skocz do pozycji: 1.

Tytuł:: Noise quantization simulation analysis of optical convolutional networks
Autorzy:: Zhang, Ye
Zhang, Saining
Zhang, Danni
Su, Yanmei
Yi, Junkai
Wang, Pengfei
Wang, Ruiting
Luo, Guangzhen
Zhou, Xuliang
Pan, Jiaoqing
Tematy:: optical neural network
convolutional neural network
noise
quantization; Pokaż więcej
Wydawca:: Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
Powiązania:: https://bibliotekanauki.pl/articles/27310111.pdf Link otwiera się w nowym oknie
Opis:: Optical neural network (ONN) has been regarded as one of the most prospective techniques in the future, due to its high-speed and low power cost. However, the realization of optical convolutional neural network (CNN) in non-ideal cases still remains a big challenge. In this paper, we propose an optical convolutional networks system for classification problems by applying general matrix multiply (GEMM) technology. The results show that under the influence of noise, this system still has good performance with low TOP-1 and TOP-5 error rates of 44.26% and 14.51% for ImageNet. We also propose a quantization model of CNN. The noise quantization model reaches a sufficient prediction accuracy of about 96% for MNIST handwritten dataset.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 2.

Tytuł:: A MZI-based optical neural network for image classification
Autorzy:: Zhang, Ye
Zhang, Saining
Zhang, Danni
Wang, Ruiting
Su, Yanmei
Yi, Junkai
Wang, Pengfei
Luo, Guangzhen
Zhou, Xuliang
Pan, Jiaoqing
Tematy:: optical neural network
image classification
Mach-Zehnder interferometer; Pokaż więcej
Wydawca:: Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
Powiązania:: https://bibliotekanauki.pl/articles/58970215.pdf Link otwiera się w nowym oknie
Opis:: In recent years, with the expansion of information, artificial intelligence technology has been developed and used in various fields. Among them, optical neural network provides a new type of special neural network accelerator chip solution, which has the advantages of high speed, high bandwidth, and low power consumption. In this paper, we construct an optical neural network based on Mach–Zehnder interferometer. The experimental results on the image classification of MNIST handwritten digitals show that the optical neural network has high accuracy, fast convergence and good scalability.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 3.

Tytuł:: Design of a photonic unitary neural network based on MZI arrays
Autorzy:: Zhang, Ye
Wang, Ruiting
Zhang, Yejin
Su, Yanmei
Wang, Pengfei
Luo, Guangzhen
Zhou, Xuliang
Pan, Jiaoqing
Tematy:: optical neural network
unitary matrix
Mach-Zehnder interferometer; Pokaż więcej
Wydawca:: Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
Powiązania:: https://bibliotekanauki.pl/articles/58970251.pdf Link otwiera się w nowym oknie
Opis:: In recent years, optical neural networks have attracted widespread attention, due to their advantages of high speed, high parallelism, high bandwidth, and low power consumption. Photonic unitary neural network is a kind of neural networks that utilize the principles of unitary matrices and photonics to perform computations. In this paper, we design a photonic unitary neural network based on Mach–Zehnder interferometer arrays. The results show that the network has a good performance on both triangular and circular binary classification datasets, where most of the data points are correctly classified. The accuracies achieve 97% and 95% for triangular and circular datasets, with the loss function values of 0.023 and 0.046, respectively.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 4.

Tytuł:: Control and measurement system of the optical neural network
System kontrolno-pomiarowy optycznej sieci neuronowej
Autorzy:: Wącław, Wojciech
Opis:: The subject of this work is the description of an electronic system used to control and carry out measurements in an optical neural network recognizing shapes on a 16-bit bitmap. The paper contains the most important information about the characteristics of optical fibers and optical data transmission, a description of the operation of Small Form-factor Pluggable modules, process description of creating a control and measurement system, a method of obtaining information through Digital Diagnostics Monitoring, a method of programming the Arduino microcontroller board that allows for sending an optical signal, as well as reading the signal power and other parameters for the diagnostics of SFP modules from EEPROM memory.
Przedmiotem niniejszej pracy jest opisanie układu elektronicznego służącego do kontroli i prowadzeniu pomiarów w optycznej sieci neuronowej rozpoznającej kształty na 16-bitowej bitmapie. W pracy zawarto najważniejsze informacje o cechach światłowodów i optycznej transmisji danych, opis działania modułów Small Form-factor Pluggable, proces powstawania systemu kontrolno-pomiarowego, metodę pozyskiwania informacji poprzez Digital Diagnostics Monitoring, sposób zaprogramowania płytki z mikrokontrolerem Arduino pozwalającym na wysyłanie sygnału optycznego, a także odczyt siły sygnału oraz innych parametrów do diagnostyki modułów SFP z pamięci EEPROM.
Dostawca treści:: Repozytorium Uniwersytetu Jagiellońskiego

Inne

na półce

Skocz do pozycji: 5.

Tytuł:: Detection of Monocrystalline Silicon Wafer Defects Using Deep Transfer Learning
Autorzy:: Ganum, Adriana
Iskandar, D. N. F. Awang
Chin, Lim Phei
Fauzi, Ahmad Hadinata
Tematy:: automated optical inspection
machine learning
neural network
wafer imperfection identification; Pokaż więcej
Wydawca:: Instytut Łączności - Państwowy Instytut Badawczy
Powiązania:: https://bibliotekanauki.pl/articles/2058502.pdf Link otwiera się w nowym oknie
Opis:: Defect detection is an important step in industrial production of monocrystalline silicon. Through the study of deep learning, this work proposes a framework for classifying monocrystalline silicon wafer defects using deep transfer learning (DTL). An existing pre-trained deep learning model was used as the starting point for building a new model. We studied the use of DTL and the potential adaptation of Mo bileNetV2 that was pre-trained using ImageNet for extracting monocrystalline silicon wafer defect features. This has led to speeding up the training process and to improving performance of the DTL-MobileNetV2 model in detecting and classifying six types of monocrystalline silicon wafer defects (crack, double contrast, hole, microcrack, saw-mark and stain). The process of training the DTL-MobileNetV2 model was optimized by relying on the dense block layer and global average pooling (GAP) method which had accelerated the convergence rate and improved generalization of the classification network. The monocrystalline silicon wafer defect classification technique relying on the DTL-MobileNetV2 model achieved the accuracy rate of 98.99% when evaluated against the testing set. This shows that DTL is an effective way of detecting different types of defects in monocrystalline silicon wafers, thus being suitable for minimizing misclassification and maximizing the overall production capacities.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 6.

Tytuł:: Subpixel localization of optical vortices using artificial neural networks
Autorzy:: Popiołek-Masajada, Agnieszka
Frączek, Ewa
Burnecka, Emilia
Tematy:: optical vortex
spiral phase map
pseudo phase
deep learning
neural network; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Czytelnia Czasopism PAN
Powiązania:: https://bibliotekanauki.pl/articles/1849005.pdf Link otwiera się w nowym oknie
Opis:: Optical vortices are getting attention in modern optical metrology. Because of their unique features, they can be used as precise position markers. In this paper, we show that an artificial neural network can be used to improve vortex localization. A deep neural network with several hidden layers was trained to find subpixel vortex positions on the spiral phase maps. Several thousand training samples, differing by spiral density, its orientation, and vortex position, were generated numerically for teaching purposes. As a result, Best Validation Performance of the order of 10-5 pixel has been reached. To verify the usefulness of the proposed method, a related experiment in the setup of an optical vortex scanning microscope has been reported. It is shown that the vortex can be localized with subpixel accuracy also on experimental phase maps.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 7.

Tytuł:: Subpixel localization of optical vortices using artificial neural networks
Autorzy:: Popiołek-Masajada, Agnieszka
Frączek, Ewa
Burnecka, Emilia
Tematy:: optical vortex
spiral phase map
pseudo phase
deep learning
neural network; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Czytelnia Czasopism PAN
Powiązania:: https://bibliotekanauki.pl/articles/1849096.pdf Link otwiera się w nowym oknie
Opis:: Optical vortices are getting attention in modern optical metrology. Because of their unique features, they can be used as precise position markers. In this paper, we show that an artificial neural network can be used to improve vortex localization. A deep neural network with several hidden layers was trained to find subpixel vortex positions on the spiral phase maps. Several thousand training samples, differing by spiral density, its orientation, and vortex position, were generated numerically for teaching purposes. As a result, Best Validation Performance of the order of 10-5 pixel has been reached. To verify the usefulness of the proposed method, a related experiment in the setup of an optical vortex scanning microscope has been reported. It is shown that the vortex can be localized with subpixel accuracy also on experimental phase maps.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 8.

Tytuł:: Using ADTS and CNN methods to effectively monitor CD, crosstalk, and OSNR in an optical network
Autorzy:: Mrozek, Tomasz
Perlicki, Krzysztof
Tematy:: optical performance monitoring
asynchronous delay-tap sampling
convolutional neural network
multi impairments monitoring; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Stowarzyszenie Elektryków Polskich
Powiązania:: https://bibliotekanauki.pl/articles/59112940.pdf Link otwiera się w nowym oknie
Opis:: The article presents the results of a method based on asynchronous delay-tap sampling (ADTS) and convolutional neural network (CNN) for determining simultaneously occurring disturbances described using the chromatic dispersion (CD), crosstalk and optical signal-to-noise ratio (OSNR) parameters. The ADTS method was used to generate training and test data for the convolutional network, which in turn was used to learn to recognize interference from said data. The tests were carried out for a transmission speed of 10 Gbit/s and for on-off keying (OOK) and differential phase shift keying (DPSK) modulation. Very good results were obtained in recognizing simultaneously occurring phenomena. Accuracy of over 99% was achieved for CD and crosstalk for DPSK modulation and over 98% for OOK modulation. In the case of amplified spontaneous emission (ASE) noise, slightly weaker results were obtained, above 95-96% for both modulations. Based on the conducted research, it was determined that the use of ADTS and CNN methods enables monitoring of simultaneously occurring CD, crosstalk, and ASE noise in the physical layer of the optical network, while maintaining the requirements for modern monitoring systems.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 9.

Tytuł:: Graph-based segmentation with homogeneous hue and texture vertices
Autorzy:: Ngo, Lua
Han, Jae-Ho
Tematy:: image segmentation
deep neural network
electron microscopy
optical coherence tomography
pattern recognition; Pokaż więcej
Wydawca:: Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
Powiązania:: https://bibliotekanauki.pl/articles/2033896.pdf Link otwiera się w nowym oknie
Opis:: This work presents an automated segmentation method, based on graph theory, which processes superpixels that exhibit spatially similarities in hue and texture pixel groups, rather than individual pixels. The graph shortest path includes a chain of neighboring superpixels which have minimal intensity changes. This method reduces graphics computational complexity because it provides large decreases in the number of vertices as the superpixel size increases. For the starting vertex prediction, the boundary pixel in first column which is included in this starting vertex is predicted by a trained deep neural network formulated as a regression task. By formulating the problem as a regression scheme, the computational burden is decreased in comparison with classifying each pixel in the entire image. This feasibility approach, when applied as a preliminary study in electron microscopy and optical coherence tomography images, demonstrated high measures of accuracy: 0.9670 for the electron microscopy image and 0.9930 for vitreous/nerve-fiber and inner-segment/outer-segment layer segmentations in the optical coherence tomography image.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 10.

Tytuł:: Sieć neuronowa lokalizująca wiry optyczne rozmieszczone w regularnej strukturze
Artificial neural network for localization of optical vortices positioned in a regular structure
Autorzy:: Guszkowski, T.
Frączek, E.
Tematy:: wir optyczny
lokalizacja
sztuczna sieć neuronowa
optical vortex
localization
artificial neural network; Pokaż więcej
Wydawca:: Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Powiązania:: https://bibliotekanauki.pl/articles/157563.pdf Link otwiera się w nowym oknie
Opis:: Praca prezentuje opartą na sztucznej sieci neuronowej metodę określania położenia wirów optycznych rozmieszczonych w regularnej strukturze i powstałych w wyniku interferencji trzech fal płaskich. Do uczenia i oceny jakości działania sieci neuronowej wykorzystano zestaw symulowanych obrazów, na które dodatkowo nałożono szum pomiarowy oraz zniekształcenia geometryczne wynikające z symulowanych drgań układu pomiarowego. W wyniku uczenia sieci neuronowej uzyskano neuronowy lokalizator wirów optycznych o medianie błędu lokalizacji poniżej 0,4 piksela.
The paper presents a short introduction to the optical vortices localization problem and an Artificial Neural Network (ANN) for localization of the optical vortices positioned in a regular structure of honeycomb. The analyzed vortices form as an effect of interference of three planar waves. A set of 1800 simulated images with added noise and geometric distortions modelling experimental setup vibrations was used for ANN learning and evaluation. As a result an unidirectional ANN with 100 inputs which correspond with pixels in a 10x10 image matrix; one non-linear hidden layer of 5 neuron and 2 outputs representing the coordinates of the vortex were created. The learning criterion was Mean Square Error (MSE) and the net was taught with Levenberg-Marquardt algorithm implemented in MATLAB. Final tests were performed with 180 images excluded from ANN learning. As a result a neuronal localizator of optical vortices was obtained with the worst-case localization error less than 2.1 pixel and localization error median less than 0.4 pixel.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Informacja

Wyszukujesz frazę "optical neural network" wg kryterium: Temat