LightOn researchers explain how they trained an AI model on an optical co-processor

Venture Beat | Jun 3, 2020 at 7:30 PM
  • In a technical paper published on the preprint server Arxiv.org, scientists at LightOn, a startup developing optical computing hardware for AI applications, detail what they claim is one of the first optical co-processors able to accelerate AI model training.
  • In experiments on the popular MNIST data set of handwritten digits, their co-processor — the Optical Processing Unit — ostensibly helped train a model to recognize digits with 95.8% accuracy, a model that when trained on a graphics card achieved 97.6% accuracy.
  • In machine learning, DFA employs random predictions of a model’s error rates as training signals.