Photonic convolutional neural network with pre-trained in-situ training

• URL: http://arxiv.org/abs/2604.02429v1
• Date: Thu, 02 Apr 2026 18:01:41 GMT
• Title: Photonic convolutional neural network with pre-trained in-situ training
• Abstract summary: Photonic computing is a computing paradigm which have great potential to overcome the energy bottlenecks of electronic von Neumann architecture.<n>We propose and validate a fully photonic convolutional neural network (PCNN) that performs MNIST image classification entirely in the optical domain.<n>Our system maintains coherent processing utilizing Mach-Zehnder interferometer (MZI) meshes, wavelength-division multiplexed (WDM) pooling, and microring resonator-based nonlinearities.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Photonic computing is a computing paradigm which have great potential to overcome the energy bottlenecks of electronic von Neumann architecture. Throughput and power consumption are fundamental limitations of Complementary-metal-oxide-semiconductor (CMOS) chips, therefore convolutional neural network (CNN) is revolutionising machine learning, computer vision and other image based applications. In this work, we propose and validate a fully photonic convolutional neural network (PCNN) that performs MNIST image classification entirely in the optical domain, achieving 94 percent test accuracy. Unlike existing architectures that rely on frequent in-between conversions from optical to electrical and back to optical (O/E/O), our system maintains coherent processing utilizing Mach-Zehnder interferometer (MZI) meshes, wavelength-division multiplexed (WDM) pooling, and microring resonator-based nonlinearities. The max pooling unit is fully implemented on silicon photonics, which does not require opto-electrical or electrical conversions. To overcome the challenges of training physical phase shifter parameters, we introduce a hybrid training methodology deploying a mathematically exact differentiable digital twin for ex-situ backpropagation, followed by in-situ fine-tuning via Simultaneous Perturbation Stochastic Approximation (SPSA) algorithm. Our evaluation demonstrates significant robustness to thermal crosstalk (only 0.43 percent accuracy degradation at severe coupling) and achieves 100 to 242 times better energy efficiency than state-of-the-art electronic GPUs for single-image inference.

Related papers

• Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification [0.0]
  This paper introduces a hybrid diffractive holographic architecture for image classification.<n>The proposed model couples a Diffractive Optical Neural Network (DONN) with a Holographic Interference-Based Learning (HIBL) operator.<n>In physics-informed simulation on MNIST, a three-layer system with approximately 25,000 phase elements achieves 91.2% test accuracy.
  arXiv  Detail & Related papers  (2026-04-14T10:34:14Z)
• SEPhIA: <1 laser/neuron Spiking Electro-Photonic Integrated Multi-Tiled Architecture for Scalable Optical Neuromorphic Computing [0.11971027459760782]
  We introduce SEPhIA, a photonic-electronic, multi-tiled SNN architecture emphasizing implementation feasibility and realistic scaling.<n> SEPhIA leverages microring resonator modulators (MRMs) and multi-wavelength sources to achieve effective sub-one-laser-per-spiking neuron efficiency.
  arXiv  Detail & Related papers  (2025-10-08T18:24:29Z)
• Accurate Ab-initio Neural-network Solutions to Large-Scale Electronic Structure Problems [52.19558333652367]
  We present finite-range embeddings (FiRE) for accurate large-scale ab-initio electronic structure calculations.<n>FiRE reduces the complexity of neural-network variational Monte Carlo (NN-VMC) by $sim ntextel$, the number of electrons.<n>We validate our method's accuracy on various challenging systems, including biochemical compounds and organometallic compounds.
  arXiv  Detail & Related papers  (2025-04-08T14:28:54Z)
• Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment [48.90869997343841]
  We experimentally implement a versatile and scalable training algorithm, called direct feedback alignment, on a hybrid electronic-photonic platform.<n>An optical processing unit performs large-scale random matrix multiplications, at speeds up to 1500 TeraOPS under 30 Watts of power.<n>We study the scaling of the training time, and demonstrate a potential advantage of our hybrid opto-electronic approach for ultra-deep and wide neural networks.
  arXiv  Detail & Related papers  (2024-09-01T12:48:47Z)
• TeMPO: Efficient Time-Multiplexed Dynamic Photonic Tensor Core for Edge AI with Compact Slow-Light Electro-Optic Modulator [44.74560543672329]
  We present a time-multiplexed dynamic photonic tensor accelerator, dubbed TeMPO, with cross-layer device/circuit/architecture customization. We achieve a 368.6 TOPS peak performance, 22.3 TOPS/W energy efficiency, and 1.2 TOPS/mm$2$ compute density. This work signifies the power of cross-layer co-design and domain-specific customization, paving the way for future electronic-photonic accelerators.
  arXiv  Detail & Related papers  (2024-02-12T03:40:32Z)
• All-optical modulation with single-photons using electron avalanche [66.27103948750306]
  We demonstrate all-optical modulation enabled by electron avalanche process in silicon.<n>Our approach opens the possibility of gigahertz-speed, and potentially even faster, optical switching at the single-photon level.
  arXiv  Detail & Related papers  (2023-12-18T20:14:15Z)
• Sophisticated deep learning with on-chip optical diffractive tensor processing [5.081061839052458]
  Photonic integrated circuits provide an efficient approach to mitigate bandwidth limitations and power-wall brought by electronic counterparts. We propose an optical computing architecture enabled by on-chip diffraction to implement convolutional acceleration, termed optical convolution unit (OCU) With OCU as the fundamental unit, we build an optical convolutional neural network (oCNN) to implement two popular deep learning tasks: classification and regression.
  arXiv  Detail & Related papers  (2022-12-20T03:33:26Z)
• Scalable Nanophotonic-Electronic Spiking Neural Networks [3.9918594409417576]
  Spiking neural networks (SNN) provide a new computational paradigm capable of highly parallelized, real-time processing. Photonic devices are ideal for the design of high-bandwidth, parallel architectures matching the SNN computational paradigm. Co-integrated CMOS and SiPh technologies are well-suited to the design of scalable SNN computing architectures.
  arXiv  Detail & Related papers  (2022-08-28T06:10:06Z)
• Quantum-limited millimeter wave to optical transduction [50.663540427505616]
  Long distance transmission of quantum information is a central ingredient of distributed quantum information processors. Current approaches to transduction employ solid state links between electrical and optical domains. We demonstrate quantum-limited transduction of millimeter-wave (mmwave) photons into optical photons using cold $85$Rb atoms as the transducer.
  arXiv  Detail & Related papers  (2022-07-20T18:04:26Z)
• Single-Shot Optical Neural Network [55.41644538483948]
  'Weight-stationary' analog optical and electronic hardware has been proposed to reduce the compute resources required by deep neural networks. We present a scalable, single-shot-per-layer weight-stationary optical processor.
  arXiv  Detail & Related papers  (2022-05-18T17:49:49Z)
• Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networks [0.7627023515997987]
  We design mass-manufacturable silicon photonic neural networks that cascade our custom designed "photonic mesh" accelerator. We demonstrate in situ backpropagation for the first time to solve classification tasks. Our findings suggest a new training paradigm for photonics-accelerated artificial intelligence based entirely on a physical analog of the popular backpropagation technique.
  arXiv  Detail & Related papers  (2022-05-17T17:13:50Z)
• Rapid characterisation of linear-optical networks via PhaseLift [51.03305009278831]
  Integrated photonics offers great phase-stability and can rely on the large scale manufacturability provided by the semiconductor industry. New devices, based on such optical circuits, hold the promise of faster and energy-efficient computations in machine learning applications. We present a novel technique to reconstruct the transfer matrix of linear optical networks.
  arXiv  Detail & Related papers  (2020-10-01T16:04:22Z)
• Photonic tensor cores for machine learning [0.0]
  We introduce an integrated photonics-based TPU to perform matrix vector multiplication and summation. We show that the performance of this 8-bit photonic TPU can be 2-3 orders higher compared to an electrical TPU whilst featuring similar chip areas. This work shows that photonic specialized processors have the potential to augment electronic systems and may perform exceptionally well in network-edge devices in the looming 5G networks and beyond.
  arXiv  Detail & Related papers  (2020-02-01T14:11:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.