Explore the vast range of titles available.

Tensor analytics lays the mathematical basis for the prosperous promotion of multiway signal processing. To increase computing throughput, mainstream processors transform tensor convolutions into matrix multiplications to enhance the parallelism of computing. However, such order-reducing transformation produces data duplicates and consumes additional memory. Here, we propose an integrated photonic tensor flow processor (PTFP) without digitally duplicating the input data. It outputs the convolved tensor as the input tensor ‘flows’ through the processor. The hybrid manipulation of optical wavelengths, space dimensions, and time delay steps, enables the direct representation and processing of high-order tensors in the optical domain. In the proof-of-concept experiment, an integrated processor manipulating wavelengths and delay steps is implemented for demonstrating the key functionalities of PTFP. The multi-channel images and videos are processed at the modulation rate of 20 Gbaud. A convolutional neural network for video action recognition is demonstrated on the processor, which achieves an accuracy of 97.9%. Convolutional operation is a very efficient way to handle tensor analytics, but it consumes a large quantity of additional memory. Here, the authors demonstrate an integrated photonic tensor processor which directly handles high-order tensors without tensor-matrix transformation.

The emergence of parallel convolution-operation technology has substantially powered the complexity and functionality of optical neural networks (ONN) by harnessing the dimension of optical wavelength. However, this advanced architecture faces remarkable challenges in high-level integration and on-chip operation. In this work, convolution based on time-wavelength plane stretching approach is implemented on a microcomb-driven chip-based photonic processing unit (PPU). To support the operation of this processing unit, we develop a dedicated control and operation protocol, leading to a record high weight precision of 9 bits. Moreover, the compact architecture and high data loading speed enable a preeminent photonic-core compute density of over 1 trillion of operations per second per square millimeter (TOPS mm −2 ). Two proof-of-concept experiments are demonstrated, including image edge detection and handwritten digit recognition, showing comparable processing capability compared to that of a digital computer. Due to the advanced performance and the great scalability, this parallel photonic processing unit can potentially revolutionize sophisticated artificial intelligence tasks including autonomous driving, video action recognition and image reconstruction. Optical neural networks face remarkable challenges in high-level integration and on-chip operation. In this work the authors enable optical convolution utilizing time-wavelength plane stretching approach on a microcomb-driven chip-based photonic processing unit.

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 the 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 the complete real-value domain instead of in only the 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 chips. It is anticipated that the OCDC can promote the novel accomplishment of ONNs in modern AI applications including autonomous driving, natural language processing, and scientific study.An optical coherent chip completes state-of-the-art image reconstruction tasks with 32-bit computer comparable image quality, showing potential in conquering sophisticated deep learning regression tasks.

In this paper, a Blockchain-driven platform for supply chain finance, BCautoSCF (Zhi-lian-che-rong in Chinese), is introduced. It is successfully established as a reliable and efficient financing platform for the auto retail industry. Due to the Blockchain built-in trust mechanism, participants in the supply chain (SC) networks work extensively and transparently to run a reliable, convenient, and traceable business. Likewise, the traditional supply chain finance (SCF), partial automation of SCF workflows with fewer human errors and disruptions was achieved through smart contract in BCautoSCF. Such open and secure features suggest the feasibility of BCautoSCF in SCF. As the first Blockchain-driven SCF application for the auto retail industry in China, our contribution lies in studying these pain points existing in traditional SCF and proposing a novel Blockchain-driven design to reshape the business logic of SCF to develop an efficient and reliable financing platform for small and medium enterprises (SMEs) in the auto retail industry to decrease the cost of financing and speed up the cash flows. Currently, there are over 600 active enterprise users that adopt BCautoSCF to run their financing business. Up to October 2019, the BCautoSCF provides services to 449 online/offline auto retailors, three B2B asset exchange platforms, nine fund providers, and 78 logistic services across 21 provinces in China. There are 3296 financing transactions successfully completed in BCautoSCF, and the amount of financing is ¥566,784,802.18. In the future, we will work towards supporting a full automation of SCF workflow by smart contracts, so that the efficiency of transaction will be further improved.

Brain-inspired photonic neural networks for artificial intelligence have attracted renewed interest. For many computational tasks, such as image recognition, speech processing and deep learning, photonic neural networks have the potential to increase the computing speed and energy efficiency on the orders of magnitude compared with digital electronics. Silicon Photonics, which combines the advantages of electronics and photonics, brings hope for the large-scale photonic neural network integration. This paper walks through the basic concept of artificial neural networks and focuses on the key devices which construct the silicon photonic neuromorphic systems. We review some recent important progress in silicon photonic neural networks, which include multilayer artificial neural networks and brain-like neuromorphic systems, for artificial intelligence. A prototype of silicon photonic artificial intelligence processor for ultra-fast neural network computing is also proposed. We hope this paper gives a detailed overview and a deeper understanding of this emerging field.

Analog feature extraction (AFE) is an appealing strategy for low-latency and efficient cognitive sensing systems since key features are much sparser than the Nyquist-sampled data. However, applying AFE to broadband radio-frequency (RF) scenarios is challenging due to the bandwidth and programmability bottlenecks of analog electronic circuitry. Here, we introduce a photonics-based scheme that extracts spatiotemporal features from broadband RF signals in the analog domain. The feature extractor structure inspired by convolutional neural networks is implemented on integrated photonic circuits to process RF signals from multiple antennas, extracting valid features from both temporal and spatial dimensions. Because of the tunability of the photonic devices, the photonic spatiotemporal feature extractor is trainable, which enhances the validity of the extracted features. Moreover, a digital-analog-hybrid transfer learning method is proposed for the effective and low-cost training of the photonic feature extractor. To validate our scheme, we demonstrate a radar target recognition task with a 4-GHz instantaneous bandwidth. Experimental results indicate that the photonic analog feature extractor tackles broadband RF signals and reduces the sampling rate of analog-to-digital converters to 1/4 of the Nyquist sampling while maintaining a high target recognition accuracy of 97.5%. Our scheme offers a promising path for exploiting the AFE strategy in the realm of cognitive RF sensing, with the potential to contribute to the efficient signal processing involved in applications such as autonomous driving, robotics, and smart factories.

Background The accurate early-stage diagnosis of gallbladder cancer (GBC) is regarded as one of the major challenges in the field of oncology. However, few studies have focused on the comprehensive classification of GBC based on multiple modalities. This study aims to develop a comprehensive diagnostic framework for GBC based on both imaging and non-imaging medical data. Methods This retrospective study reviewed 298 clinical patients with gallbladder disease or volunteers from two devices. A novel end-to-end interpretable diagnostic framework for GBC is proposed to handle multiple medical modalities, including CT imaging, demographics, tumor markers, coagulation function tests, and routine blood tests. To achieve better feature extraction and fusion of the imaging modality, a novel global-hybrid-local network, namely GHL-Net, has also been developed. The ensemble learning strategy is employed to fuse multi-modality data and obtain the final classification result. In addition, two interpretable methods are applied to help clinicians understand the model-based decisions. Model performance was evaluated through accuracy, precision, specificity, sensitivity, F1-score, area under the curve (AUC), and matthews correlation coefficient (MCC). Results In both binary and multi-class classification scenarios, the proposed method showed better performance compared to other comparison methods in both datasets. Especially in the binary classification scenario, the proposed method achieved the highest accuracy, sensitivity, specificity, precision, F1-score, ROC-AUC, PR-AUC, and MCC of 95.24%, 93.55%, 96.87%, 96.67%, 95.08%, 0.9591, 0.9636, and 0.9051, respectively. The visualization results obtained based on the interpretable methods also demonstrated a high clinical relevance of the intermediate decision-making processes. Ablation studies then provided an in-depth understanding of our methodology. Conclusion The machine learning-based framework can effectively improve the accuracy of GBC diagnosis and is expected to have a more significant impact in other cancer diagnosis scenarios.

Sharing the hardware platform between diverse information systems to establish full cooperation among different functionalities has attracted substantial attention. However, broadband multifunctional integrated systems with large operating frequency ranges are challenging due to the bandwidth and computing speed restrictions of electronic circuitry. Here, we report an analog parallel processor (APP) based on the silicon photonic platform that directly discretizes and parallelizes the broadband signal in the analog domain. The APP first discretizes the signal with the optical frequency comb and then adopts optical dynamic phase interference to reassign the analog signal into 2 N parallel sequences. Via photonic analog parallelism, data rate and data volume in each sequence are simultaneously compressed, which mitigates the requirement on each parallel computing core. Moreover, the fusion of the outputs from each computing core is equivalent to directly processing broadband signals. In the proof-of-concept experiment, two-channel analog parallel processing of broadband radar signals and high-speed communication signals is implemented on the single photonic integrated circuit. The bandwidth of broadband radar signal is 6 GHz and the range resolution of 2.69 cm is achieved. The wireless communication rate of 8 Gbit/s is also validated. Breaking the bandwidth and speed limitations of the single-computing core along with further exploring the multichannel potential of this architecture, we anticipate that the proposed APP will accelerate the development of powerful opto-electronic processors as critical support for applications such as satellite networks and intelligent driving. The principle and architecture of analog parallel processor for broadband multifunctional integrated system.

The demand for versatility and finer resolution drives phased array radars to develop towards multi-band operating. However, the bandwidth limitations of conventional electronic devices make multi-band manipulation of frequency and phase rather challenging. This paper introduces a joint phase–frequency distribution manipulation method. By introducing a time delay line after optical pulses, the frequency conversion and phase shift are tightly coupled. Then, the phase–frequency–time mapping for multi-band signals in a single phased array system is established. The generation, transmission, and reception of multi-band signals are simultaneously achieved. Our approach enables multi-band frequency conversion and phase shifting in a single hardware framework, ensuring synchronization and coherence across multiple bands. We experimentally demonstrate the generation, frequency conversion, and phase control of signals across four bands (S, X, Ku, and K). Beamforming and data fusion of four-band linear frequency-modulated signals with a total bandwidth of 4 GHz are achieved, resulting in a four-fold improvement in range resolution. It is also verified that the number of bands and total bandwidth can be further expanded through channel interleaving.

In complex scenarios, radar echoes are contaminated by strong jamming, which significantly degrades their detection. Target detection under ultra-low signal-to-jamming ratio (SJR) conditions has thus become a major challenge when confronted with active jamming represented by smeared spectrum (SMSP) noise. Traditional jamming suppression methods are often limited by model dependency and useful signal loss. Convolutional neural networks (CNNs) have gained significant attention as an effective method for jamming suppression. However, in an ultra-low SJR environment, CNNs would have difficulty in carrying out jamming suppression, resulting in poor signal quality. In this study, we utilize a bandwidth enhancement method to allow CNNs to perform effective radar active jamming suppression in ultra-low SJR environments. Specifically, the bandwidth enhancement method reduces the correlation between target and jamming signals, which yields higher-quality target range profiles. Consequently, a modified CNN featuring a dense connection module can effectively suppress jamming even in ultra-low SJR scenarios. The experimental results show that when the input SJR is −30 dB and the bandwidth is 1.2 GHz, the output SJR reaches 13.25 dB. Meanwhile, the improvement factor (IF) gradually increases and reaches saturation at ~15 dB. Building on the bandwidth enhancement method, the modified CNN further improves the IF by ~27 dB. This work is expected to offer a new technical pathway for suppressing radar active jamming in ultra-low SJR scenarios.