paper-with-me

홈 › Papers

Light-in-the-loop: using a photonics co-processor for scalable training of neural networks

2020-06-02 · Julien Launay, Iacopo Poli, Kilian Müller, Igor Carron, Laurent Daudet, Florent Krzakala, Sylvain Gigan

As neural networks grow larger and more complex and data-hungry, training costs are skyrocketing. Especially when lifelong learning is necessary, such as in recommender systems or self-driving cars, this might soon become unsustainable. In this study, we present the first optical co-processor able to accelerate the training phase of digitally-implemented neural networks. We rely on direct feedback alignment as an alternative to backpropagation, and perform the error projection step optically. Leveraging the optical random projections delivered by our co-processor, we demonstrate its use to train a neural network for handwritten digits recognition.

📄 PDF Abstract BibTeX arXiv:2006.01475

Code (0)

등록된 구현이 없습니다.

Tasks

Lifelong learningRecommendation SystemsSelf-Driving Cars

Similar Papers 제목 키워드 기반

Photonics for artificial intelligence and neuromorphic computing

2020-10-30 · Bhavin J. Shastri, Alexander N. Tait, Thomas Ferreira de Lima, Wolfram H. P. Pernice 외

Research in photonic computing has flourished due to the proliferation of optoelectronic components on photonic integration platforms. Photonic integrated circuits have enabled ultrafast artificial neural networks, provi…

Medical Diagnosis

Harnessing Photonics for Machine Intelligence

2026-04-12 · Hanqing Zhu, Shupeng Ning, Hongjian Zhou, Ziang Yin 외 arxiv

The exponential growth of machine-intelligence workloads is colliding with the power, memory, and interconnect limits of the post-Moore era, motivating compute substrates that scale beyond transistor density alone. Integ…

A complete, parallel and autonomous photonic neural network in a semiconductor multimode laser

2020-12-21 · Xavier Porte, Anas Skalli, Nasibeh Haghighi, Stephan Reitzenstein 외

Neural networks are one of the disruptive computing concepts of our time. However, they fundamentally differ from classical, algorithmic computing in a number of fundamental aspects. These differences result in equally f…

Mixed-signal implementation of feedback-control optimizer for single-layer Spiking Neural Networks

2026-03-25 · Jonathan Haag, Christian Metzner, Dmitrii Zendrikov, Giacomo Indiveri 외 arxiv

On-chip learning is key to scalable and adaptive neuromorphic systems, yet existing training methods are either difficult to implement in hardware or overly restrictive. However, recent studies show that feedback-control…

Binary Classification

High-speed multiwavelength photonic temporal integration using silicon photonics

2025-05-07 · Yi Zhang, Nikolaos Farmakidis, Ioannis Roumpos, Miltiadis Moralis-Pegios 외

Optical systems have been pivotal for energy-efficient computing, performing high-speed, parallel operations in low-loss carriers. While these predominantly analog optical accelerators bypass digitization to perform para…