Add workshop agenda

[anssiko]

No description provided.

[anssiko]

Below is the agenda for the W3C Workshop on Web and Machine Learning live session scheduled September 16, 2020, 2pm UTC.

If your GitHub username is associated with a topic, you have been identified as a contributor in the area and you are invited to share your perspectives on the topic during the live session discussions.

Meeting logistics will be shared separately.

September 16, 2020, 2pm UTC 🗓️

🔎 Scope: Opportunities and Challenges of Browser-Based Machine Learning

✅ Goal: Determine what are the unique opportunities of browser-based ML, what are the obstacles hindering adoption

👋 Introduction to the workshop - @anssiko @dontcallmedom

💡 "Opportunities and Challenges" discussion topics:

ℹ️ WebGPU fitness for ML frameworks #66 - @jasonmayes @Kangz @grorg

❓ Does WebGPU expose the right API surface to support ML frameworks interactions with GPUs?
✔️ Proposal: New WebGPU extensions for subgroups, cooperative matrix multiply.

ℹ️ Applicability to non-browser JS environments #62 - @jasonmayes @phoddie @huningxin @WenheLI

❓ Pay attention to the applicability of the browser-targeted work to non-browser JS environments, in particular Node.js.
✔️ Proposal: Extend W3C coordination to TC53 and non-browser projects.

ℹ️ Protecting ML models #67 - @jasonmayes @tidoust @pyu10055 @jbingham

❓ Some ML providers need to ensure their ML models cannot be extracted from a browser app.
✔️ Proposal: Investigate existing access control mechanisms for video, learnings from 3D assets.

ℹ️ Support for Float16 in JS & Wasm environments #64 - @cynthia @jasonmayes

❓ Lack of support for float16 in JS and Wasm environments problematic for quantized models.
✔️ Proposal: TBD

ℹ️ In-browser training #82 and Training across devices #83 - @irealva @cynthia

❓ The current in-browser efforts are focused on inference rather than training.
✔️ Proposal: Understand successful real-world usages (e.g. Teachable Machine) and target transfer learning as the initial training use case for related browser API work.

ℹ️ Permission model for Machine Learning APIs #72 - @cynthia @dontcallmedom @anssiko

❓ How to design a forward-looking permission model for ML APIs?
✔️ Proposal: TBD

[anssiko]

Added a new topic for the September 16, 2020, 2pm UTC discussions:

ℹ️ Memory copies #93 - @aboba @wchao1115

❓ Machine learning apps within the browser using the media pipeline trigger many more memory copies compared with native applications hindering performance.
✔️ Proposal: Introduce a more direct way to feed a video frame, possibly captured from a camera, to a ML model.

[anssiko]

All - here's the topical organization for Sep 16, PTAL:
https://github.com/w3c/machine-learning-workshop/tree/master/agenda (edit: now published)

@dontcallmedom we're ready to announce, feel tree to merge and announce if this looks good to you.