Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPhotonic convolutional neural networks using integrated diffractive optics
139
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
With recent rapid advances in photonic integrated circuits, it has been demonstrated that programmable photonic chips can be used to implement artificial neural networks. Convolutional neural networks (CNN) are a class of deep learning methods that have been highly successful in applications such as image classification and speech processing. We present an architecture to implement a photonic CNN using the Fourier transform property of integrated star couplers. We show, in computer simulation, high accuracy image classification using the MNIST dataset. We also model component imperfections in photonic CNN and show that the performance degradation can be recovered in a programmable chip. Our proposed architecture provides a large reduction in physical footprint compared to current implementations as it utilizes the natural advantages of optics and hence offers a scalable pathway towards integrated photonic deep learning processors.
rate research
Read More
Replacing electrons with photons is a compelling route towards light-speed, highly parallel, and low-power artificial intelligence computing. Recently, all-optical diffractive neural deep neural networks have been demonstrated. However, the existing architectures often comprise bulky components and, most critically, they cannot mimic the human brain for multitasking. Here, we demonstrate a multi-skilled diffractive neural network based on a metasurface device, which can perform on-chip multi-channel sensing and multitasking at the speed of light in the visible. The metasurface is integrated with a complementary metal oxide semiconductor imaging sensor. Polarization multiplexing scheme of the subwavelength nanostructures are applied to construct a multi-channel classifier framework for simultaneous recognition of digital and fashionable items. The areal density of the artificial neurons can reach up to 6.25x106/mm2 multiplied by the number of channels. Our platform provides an integrated solution with all-optical on-chip sensing and computing for applications in machine vision, autonomous driving, and precision medicine.
Digital-to-analog converters (DAC) are indispensable functional units in signal processing instrumentation and wide-band telecommunication links for both civil and military applications. Since photonic systems are capable of high data throughput and low latency, an increasingly found system limitation stems from the required domain-crossing such as digital-to-analog, and electronic-to-optical. A photonic DAC implementation, in contrast, enables a seamless signal conversion with respect to both energy efficiency and short signal delay, often require bulky discrete optical components and electric-optic transformation hence introducing inefficiencies. Here, we introduce a novel coherent parallel photonic DAC concept along with an experimental demonstration capable of performing this digital-to-analog conversion without optic-electric-optic domain crossing. This design hence guarantees a linear intensity weighting among bits operating at high sampling rates, yet at a reduced footprint and power consumption compared to other photonic alternatives. Importantly, this photonic DAC could create seamless interfaces of next-generation data processing hardware for data-centers, task-specific compute accelerators such as neuromorphic engines, and network edge processing applications.
In congested electromagnetic environments, cognitive radios require knowledge about other emitters in order to optimize their dynamic spectrum access strategy. Deep learning classification algorithms have been used to recognize the wireless signal standards of emitters with high accuracy, but are limited to classifying signal classes that appear in their training set. This diminishes the performance of deep learning classifiers deployed in the field because they cannot accurately identify signals from classes outside of the training set. In this paper, a convolution neural network based open set classifier is proposed with the ability to detect if signals are not from known classes by thresholding the output sigmoid activation. The open set classifier was trained on 4G LTE, 5G NR, IEEE 802.11ax, Bluetooth Low Energy 5.0, and Narrowband Internet-of-Things signals impaired with Rayleigh or Rician fading, AWGN, frequency offsets, and in-phase/quadrature imbalances. Then, the classifier was tested on OFDM, SC-FDMA, SC, AM, and FM signals, which did not appear in the training set classes. The closed set classifier achieves an average accuracy of 94.5% for known signals with SNRs greater than 0 dB, but by design, has a 0% accuracy detecting signals from unknown classes. On the other hand, the open set classifier retains an 86% accuracy for known signal classes, but can detect 95.5% of signals from unknown classes with SNRs greater than 0 dB.
At present, there are a large number of quantum neural network models to deal with Euclidean spatial data, while little research have been conducted on non-Euclidean spatial data. In this paper, we propose a novel quantum graph convolutional neural network (QGCN) model based on quantum parametric circuits and utilize the computing power of quantum systems to accomplish graph classification tasks in traditional machine learning. The proposed QGCN model has a similar architecture as the classical graph convolutional neural networks, which can illustrate the topology of the graph type data and efficiently learn the hidden layer representation of node features as well. Numerical simulation results on a graph dataset demonstrate that the proposed model can be effectively trained and has good performance in graph level classification tasks.
This paper investigates the problem of classification of unmanned aerial vehicles (UAVs) from radio frequency (RF) fingerprints at the low signal-to-noise ratio (SNR) regime. We use convolutional neural networks (CNNs) trained with both RF time-series images and the spectrograms of 15 different off-the-shelf drone controller RF signals. When using time-series signal images, the CNN extracts features from the signal transient and envelope. As the SNR decreases, this approach fails dramatically because the information in the transient is lost in the noise, and the envelope is distorted heavily. In contrast to time-series representation of the RF signals, with spectrograms, it is possible to focus only on the desired frequency interval, i.e., 2.4 GHz ISM band, and filter out any other signal component outside of this band. These advantages provide a notable performance improvement over the time-series signals-based methods. To further increase the classification accuracy of the spectrogram-based CNN, we denoise the spectrogram images by truncating them to a limited spectral density interval. Creating a single model using spectrogram images of noisy signals and tuning the CNN model parameters, we achieve a classification accuracy varying from 92% to 100% for an SNR range from -10 dB to 30 dB, which significantly outperforms the existing approaches to our best knowledge.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
