PulseAugur
EN
LIVE 15:35:05

Programmable Waveguide Enables Single-Pass Neural Network Inference

Researchers have developed a novel two-dimensional programmable waveguide that utilizes parallel electro-optic modulation to control multimode wave propagation. This device allows for arbitrary control of light, enabling neural network inference in a single pass without digital pre-processing. The technology promises more space-efficient photonic processors with potential scaling benefits for computational tasks. AI

RANK_REASON The cluster contains an academic paper detailing a new technological approach for machine learning. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Tatsuhiro Onodera, Martin M. Stein, Benjamin A. Ash, Mandar M. Sohoni, Melissa Bosch, Ryotatsu Yanagimoto, Marc Jankowski, Timothy P. McKenna, Tianyu Wang, Gennady Shvets, Maxim R. Shcherbakov, Logan G. Wright, Peter L. McMahon ·

    Arbitrary control over multimode wave propagation for machine learning

    arXiv:2402.17750v2 Announce Type: replace-cross Abstract: Controlled multimode wave propagation can enable more space-efficient photonic processors than architectures based on discrete components connected by single-mode waveguides. Instead of defining discrete elements, one can …