WebNN seeks to enable web applications and frameworks to take advantage of native operating system services for machine learning and the underlying hardware capabilities available on a user's computer to implement consistent, efficient, and reliable ML experiences on the web.
Provide web applications and frameworks with the ability to take advantage of native operating system services for machine learning and the underlying hardware innovations available on the user's computers to implement consistent, efficient, and reliable ML experiences on the web platform.
Samples: https://webmachinelearning.github.io/webnn-samples https://microsoft.github.io/webnn-developer-preview
Explainers: https://github.com/webmachinelearning/webnn/blob/main/explainer.md