Convolutional neural networks (CNNs) have transformed image processing, but the energy consumption and inference latency of electronic based implementations remain fundamental bottlenecks. These limitations have motivated the search for alternative hardware architectures beyond Complementary metal-oxide-semiconductor (CMOS) chips. Optical systems can perform linear matrix operations at the speed of light with extremely low energy dissipation, making them attractive for CNN acceleration. However, building a fully coherent photonic CNN that performs both linear and nonlinear operations and training it efficiently remains an open challenge. Here we present a fully photonic convolutional neural network (PCNN) that executes image classification in the optical domain, including convolution, max-pooling, nonlinear activation, and fully connected layers. The network achieves 94.49 percent accuracy on the MNIST dataset distributed across Mach Zehnder Interferometer (MZI) meshes, weighted Multimode Interferometer (MMI) trees, and a microring resonator based nonlinearity. A mathematically exact differentiable digital twin, enables backpropagation for ex situ pre training, reaches 97.45 percent digital accuracy. Trained phases are transferred one-to-one to the photonic hardware and refined via a gradient free algorithm that estimates the full gradient with only two forward passes. The architecture exhibits inherent robustness to non idealities, under the compound effect of propagation loss, MZI insertion loss, fabrication disorder, and thermal crosstalk. A bottom-up power analysis yields 10.83 W static chip consumption and 843 ns inference latency, translating to 220 to 330 times greater energy efficiency than state of the art electronic GPUs for single-image inference.
In this work we numerically analyze a passive photonic integrated neuromorphic accelerator based on hardware-friendly optical spectrum slicing nodes. The proposed scheme can act as a fully analogue convolutional layer, preprocessing information directly in the optical domain. The proposed scheme allows the extraction of meaningful spatio-temporal features from the incoming data, thus when used prior to a simple fully connected digital single layer network it can boost performance with negligible power consumption. Numerical simulations using the MNIST dataset confirmed the acceleration propert…
Convolutional Neural Networks (CNN) have been the centerpiece of many applications including but not limited to computer vision, speech processing, and Natural Language Processing (NLP). However, the computationally expensive convolution operations impose many challenges to the performance and scalability of CNNs. In parallel, photonic systems, which are traditionally employed for data communication, have enjoyed recent popularity for data processing due to their high bandwidth, low power consumption, and reconfigurability. Here we propose a Photonic Convolutional Neural Network Accelerator (P…
Silicon-photonics-based optical neural network (ONN) is a promising hardware platform that could represent a paradigm shift in efficient AI with its CMOS-compatibility, flexibility, ultra-low execution latency, and high energy efficiency. In-situ training on the online programmable photonic chips is appealing but still encounters challenging issues in on-chip implementability, scalability, and efficiency. In this work, we propose a closed-loop ONN on-chip learning framework L2ight to enable scalable ONN mapping and efficient in-situ learning. L2ight adopts a three-stage learning flow that firs…
Neural Networks (NNs) have become the mainstream technology in the artificial intelligence (AI) renaissance over the past decade. Among different types of neural networks, convolutional neural networks (CNNs) have been widely adopted as they have achieved leading results in many fields such as computer vision and speech recognition. This success in part is due to the widespread availability of capable underlying hardware platforms. Applications have always been a driving factor for design of such hardware architectures. Hardware specialization can expose us to novel architectural solutions, wh…
The parallelism of optics and the miniaturization of optical components using nanophotonic structures, such as metasurfaces present a compelling alternative to electronic implementations of convolutional neural networks. The lack of a low-power optical nonlinearity, however, requires slow and energy-inefficient conversions between the electronic and optical domains. Here, we design an architecture which utilizes a single electrical to optical conversion by designing a free-space optical frontend unit that implements the linear operations of the first layer with the subsequent layers realized e…
Convolutional Neural Networks (CNNs) are a class of Artificial Neural Networks(ANNs) that employ the method of convolving input images with filter-kernels for object recognition and classification purposes. In this paper, we propose a photonics circuit architecture which could consume a fraction of energy per inference compared with state of the art electronics.
Department of Electrical and Electronic Engineering（电子与电气工程系）；Imperial College London（帝国理工学院）；Imperial Centre for Quantum Engineering, Science and Technology（帝国量子工程、科学与技术中心）；Blackett Laboratory, Department of Physics（布莱克特实验室，物理系）；Graduate Institute of Applied Physics（应用物理研究院）；Brookhaven National Laboratory（布鲁赫斯国家实验室）；Quantum Information Center（量子信息中心）；Master Program in Intelligent Computing and Big Data（智能计算与大数据硕士项目）；Chung Yuan Christian University；JIJ
Photonic waveguides are prime candidates for integrated and parallel photonic interconnects. Such interconnects correspond to large-scale vector matrix products, which are at the heart of neural network computation. However, parallel interconnect circuits realized in two dimensions, for example by lithography, are strongly limited in size due to disadvantageous scaling. We use three dimensional (3D) printed photonic waveguides to overcome this limitation. 3D optical-couplers with fractal topology efficiently connect large numbers of input and output channels, and we show that the substrate's f…
Convolutional neural networks have become an essential element of spatial deep learning systems. In the prevailing architecture, the convolution operation is performed with Fast Fourier Transforms (FFT) electronically in GPUs. The parallelism of GPUs provides an efficiency over CPUs, however both approaches being electronic are bound by the speed and power limits of the interconnect delay inside the circuits. Here we present a silicon photonics based architecture for convolutional neural networks that harnesses the phase property of light to perform FFTs efficiently. Our all-optical FFT is bas…
University of California, Los Angeles（加州大学洛杉矶分校）；The George Washington University（乔治华盛顿大学）
The last few years have seen a lot of work to address the challenge of low-latency and high-throughput convolutional neural network inference. Integrated photonics has the potential to dramatically accelerate neural networks because of its low-latency nature. Combined with the concept of Joint Transform Correlator (JTC), the computationally expensive convolution functions can be computed instantaneously (time of flight of light) with almost no cost. This 'free' convolution computation provides the theoretical basis of the proposed PhotoFourier JTC-based CNN accelerator. PhotoFourier addresses …
The 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 (GPUs). However, electronics systems are limited with respect to power dissipation and delay, both, 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 exec…
UC San Diego（加州大学圣迭戈分校）；Micron Technology（美光科技）；Colorado State University（科罗拉多州立大学）；Texas A&M University（得克萨斯A&M大学）
Training deep learning networks involves continuous weight updates across the various layers of the deep network while using a backpropagation algorithm (BP). This results in expensive computation overheads during training. Consequently, most deep learning accelerators today employ pre-trained 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…
Deep learning is highly pervasive in today's data-intensive era. In particular, convolutional neural networks (CNNs) are being widely adopted in a variety of fields for superior accuracy. However, computing deep CNNs on traditional CPUs and GPUs brings several performance and energy pitfalls. Several novel approaches based on ASIC, FPGA, and resistive-memory devices have been recently demonstrated with promising results. Most of them target only the inference (testing) phase of deep learning. There have been very limited attempts to design a full-fledged deep learning accelerator capable of bo…
Light-Bound Transformers: Hardware-Anchored Robustness for Silicon-Photonic Computer Vision Systems
Case Western Reserve University（凯斯西储大学）；New Jersey Institute of Technology（新泽理工学院）；Intel Corporation（英特尔公司）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；University of California, Irvine（加州大学尔湾分校）；Colorado State University（科罗拉多州立大学）
