arXiv subjects

Shaofu Xu

Publications and source records attributed to Shaofu Xu.

8 recordsLinked to original sources

arXiv2025

Physical Computing at the Data Processing Inequality Limit

Wave-physics-based intelligent sensing has driven multidisciplinary applications from smart industries to decision-making systems. Traditional sensing paradigms transform physical waveforms into human-understandable intermediate representations through preprocessing. Such transformations inherently cause information loss owing to data processing inequality (DPI). Here, we established a theoretical framework for physical computing at the DPI upper limit. Physical computing avoids information loss during preprocessing by directly extracting information from physical waveforms, achieving the theoretical maximum of accessible information as determined by the DPI. Furthermore, physical computing comprehensively utilizes multiple dimensions of physical waveforms, thereby enhancing the upper limit of information capture capability. Electromagnetic sensing experiments have demonstrated that physical computing can achieve 100% sensing accuracy, substantially outperforming traditional sensing paradigms. The proposed theoretical framework of physical computing offers a promising path towards enhancing the information-capture capability of next-generation intelligent sensing systems.

physics.app-ph↗

arXiv2022

High-resolution and reliable automatic target recognition based on photonic ISAR imaging system with explainable deep learning

Automatic target recognition (ATR) based on inverse synthetic aperture radar (ISAR) images, which is extensively utilized to surveil environment in military and civil fields, must be high-precision and reliable. Photonic technologies' advantage of broad bandwidth enables ISAR systems to realize high-resolution imaging, which is in favor of achieving high-performance ATR. Deep learning (DL) algorithms have achieved excellent recognition accuracies. However, the lack of interpretability of DL algorithms causes the head-scratching problem of credibility. In this paper, we exploit the inner relationship between a photonic ISAR imaging system and behaviors of a convolutional neural network (CNN) to deeply comprehend the intelligent recognition. Specifically, we manipulate imaging physical process and analyze network outputs, the relevance between the ISAR image and network output, and the visualization of features in the network output layer. Consequently, the broader imaging bandwidths and appropriate imaging angles lead to more detailed structural and contour features and the bigger discrepancy among ISAR images of different targets, which contributes to the CNN recognizing and distinguishing objects according to physical laws. Then, based on the photonic ISAR imaging system and the explainable CNN, we accomplish a high-accuracy and reliable ATR. To the best of our knowledge, there is no precedent of explaining the DL algorithms by exploring the influence of the physical process of data generation on network behaviors. It is anticipated that this work can not only inspire the accomplishment of a high-performance ATR but also bring new insights to explore network behaviors and thus achieve better intelligent abilities.

eess.SP↗

arXiv2021

High-order tensor flow processing using integrated photonic circuits

Tensor analytics lays mathematical basis for the prosperous promotion of multiway signal processing. To increase computing throughput, mainstream processors transform tensor convolutions to matrix multiplications to enhance parallelism of computing. However, such order-reducing transformation produces data duplicates and consumes additional memory. Here, we demonstrate an integrated photonic tensor flow processor without tensor-matrix transformation, which outputs the convolved tensor as the input tensor 'flows' through the processor. The hybrid manipulation of optical dimensions of wavelength, time, and space enables the direct representation and processing of high-order tensors in optical domain. In the proof-of-concept experiment, processing of multi-channel images and videos is accomplished at the frequency of 20 GHz. A convolutional neural network is demonstrated on the processor, which achieves an accuracy of 97.9 percent on action recognition.

cs.ET↗

arXiv2021

Optical coherent dot-product chip for sophisticated deep learning regression

Optical implementations of neural networks (ONNs) herald the next-generation high-speed and energy-efficient deep learning computing by harnessing the technical advantages of large bandwidth and high parallelism of optics. However, due to the problems of incomplete numerical domain, limited hardware scale, or inadequate numerical accuracy, the majority of existing ONNs were studied for basic classification tasks. Given that regression is a fundamental form of deep learning and accounts for a large part of current artificial intelligence applications, it is necessary to master deep learning regression for further development and deployment of ONNs. Here, we demonstrate a silicon-based optical coherent dot-product chip (OCDC) capable of completing deep learning regression tasks. The OCDC adopts optical fields to carry out operations in complete real-value domain instead of in only positive domain. Via reusing, a single chip conducts matrix multiplications and convolutions in neural networks of any complexity. Also, hardware deviations are compensated via in-situ backpropagation control provided the simplicity of chip architecture. Therefore, the OCDC meets the requirements for sophisticated regression tasks and we successfully demonstrate a representative neural network, the AUTOMAP (a cutting-edge neural network model for image reconstruction). The quality of reconstructed images by the OCDC and a 32-bit digital computer is comparable. To the best of our knowledge, there is no precedent of performing such state-of-the-art regression tasks on ONN chip. It is anticipated that the OCDC can promote novel accomplishment of ONNs in modern AI applications including autonomous driving, natural language processing, and scientific study.

cs.ET↗

arXiv2020

Hardware-irrelevant parallel processing system

Parallel processing technology has been a primary tool for achieving high-speed, high-accuracy, and broadband processing for many years across modern information systems and data processing such as optical and radar, synthetic aperture radar imaging, digital beam forming, and digital filtering systems. However, hardware deviations in a parallel processing system (PPS) severely degrade system performance and pose an urgent challenge. We propose a hardware-irrelevant PPS of which the performance is unaffected by hardware deviations. In this system, an embedded convolutional recurrent autoencoder (CRAE), which learns inherent system patterns as well as acquires and removes adverse effects brought by hardware deviations, is adopted. We implement a hardware-irrelevant PPS into a parallel photonic sampling system to accomplish a high-performance analog-to-digital conversion for microwave signals with high frequency and broad bandwidth. Under one system state, a category of signals with two different mismatch degrees is utilized to train the CRAE, which can then compensate for mismatches in various categories of signals with multiple mismatch degrees under random system states. Our approach is extensively applicable to achieving hardware-irrelevant PPSs which are either discrete or integrated in photonic, electric, and other fields.

eess.SP↗

arXiv2020

Performance evaluation of an integrated photonic convolutional neural network based on delay buffering and wavelength division multiplexing

Photonic technologies have shown a promising way to build high-speed and high-energy-efficiency neural network accelerators. In previously presented photonic neural networks, architectures are mainly designed for fully-connected layers. When convolutional layers are executed in such neural networks, the large-scale electrooptic modulation array heavily increases the energy dissipation on chip. To increase the energy efficiency, here we show an integrated photonic architecture specifically for convolutional layer calculations. Optical delay lines replace electronics to execute data manipulations on optical chip, reducing the scale of electro-optic modulation array. Consequently, the energy dissipation of these parts is mitigated. Powered by wavelength division multiplexing, the footprint of delay lines is significantly reduced compared with previous art, thus being practical to fabricate. We evaluate the potential performance of the proposed architecture with respect to component flaws in practical fabrications. According to the results, with well-controlled system insertion loss, energy efficiency of the proposed architecture would surpass previously presented works and the state-of-art electronic processors. We anticipate the proposed architecture is beneficial for future fast and energy-efficient convolutional neural network accelerators.

eess.SP↗

arXiv2019

Deep learning scheme for recovery of broadband microwave photonic receiving systems in transceivers without expert knowledge and system priors

In regular microwave photonic (MWP) receiving systems, broadband signals are processed in the analog domain before they are transformed to the digital domain for further processing and storage. However, the quality of the signals may be degraded by defective photonic analog links, especially in a complicated MWP system. Here, we show a unified deep learning scheme that recovers the distorted broadband signals as they are transformed to the digital domain. The neural network could automatically learn the end-to-end inverse responses of the distortion effects of actual photonic analog links from data without expert knowledge and system priors. Hence, by shifting or augmenting the datasets, the neural network is potential to be generalized to various MWP receiving systems. We conduct experiments by nontrivial MWP systems with complicated waveforms. Results validate the effectiveness, general applicability and the noise-robustness of the proposed scheme, showing its superior performance in practical MWP systems. Therefore, the proposed deep learning scheme facilitates the low-cost performance improvement of MWP receiving systems, as well as the next-generation broadband transceivers, including radars, communications, and microwave imaging.

eess.SP↗

arXiv2018

Analog-to-digital conversion revolutionized by deep learning

As the bridge between the analog world and digital computers, analog-to-digital converters are generally used in modern information systems such as radar, surveillance, and communications. For the configuration of analog-to-digital converters in future high-frequency broadband systems, we introduce a revolutionary architecture that adopts deep learning technology to overcome tradeoffs between bandwidth, sampling rate, and accuracy. A photonic front-end provides broadband capability for direct sampling and speed multiplication. Trained deep neural networks learn the patterns of system defects, maintaining high accuracy of quantized data in a succinct and adaptive manner. Based on numerical and experimental demonstrations, we show that the proposed architecture outperforms state-of-the-art analog-to-digital converters, confirming the potential of our approach in future analog-to-digital converter design and performance enhancement of future information systems.

eess.SP↗