|
| 1 | +# W3C Workshop on Web and Machine Learning |
| 2 | + |
| 3 | +![Agenda header image][header] |
| 4 | + |
| 5 | +# Agenda for Live Sessions |
| 6 | + |
| 7 | +## September 16, 2020, 2pm UTC [🗓️](https://www.timeanddate.com/worldclock/fixedtime.html?iso=20200916T14) |
| 8 | + |
| 9 | +>🔎 **Scope:** Opportunities and Challenges of Browser-Based Machine Learning |
| 10 | +> |
| 11 | +>✅ **Goal:** Determine what are the unique opportunities of browser-based ML, what are the obstacles hindering adoption |
| 12 | +
|
| 13 | +👋 Introduction to the workshop - @anssiko @dontcallmedom |
| 14 | + |
| 15 | +[💡 "Opportunities and Challenges" discussion topics](https://github.com/w3c/machine-learning-workshop/issues?q=is%3Aissue+is%3Aopen+label%3A%22Opportunities+and+Challenges%22+sort%3Acomments-desc): |
| 16 | + |
| 17 | +## Improving existing web platform capabilities |
| 18 | + |
| 19 | +ℹ️ [WebGPU fitness for ML frameworks #66](https://github.com/w3c/machine-learning-workshop/issues/66) - @jasonmayes @Kangz @grorg |
| 20 | +- ❓ Does WebGPU expose the right API surface to support ML frameworks interactions with GPUs? |
| 21 | +- ✔️ Proposal: New WebGPU extensions for subgroups, cooperative matrix multiply. |
| 22 | + |
| 23 | +ℹ️ [Support for Float16 in JS & Wasm environments #64](https://github.com/w3c/machine-learning-workshop/issues/64) - @cynthia @jasonmayes |
| 24 | +- ❓ Lack of support for float16 in JS and Wasm environments problematic for quantized models. |
| 25 | +- ✔️ Proposal: TBD |
| 26 | + |
| 27 | +ℹ️ [Memory copies #93](https://github.com/w3c/machine-learning-workshop/issues/93) - @aboba @wchao1115 |
| 28 | +- ❓ Machine learning apps within the browser using the media pipeline trigger many more memory copies compared with native applications hindering performance. |
| 29 | +- ✔️ Proposal: Introduce a more direct way to feed a video frame, possibly captured from a camera, to a ML model. |
| 30 | + |
| 31 | +ℹ️ [Permission model for Machine Learning APIs #72](https://github.com/w3c/machine-learning-workshop/issues/72) - @cynthia @dontcallmedom @anssiko |
| 32 | +- ❓ How to design a forward-looking permission model for ML APIs? |
| 33 | +- ✔️ Proposal: TBD |
| 34 | + |
| 35 | +## Extending beyond the browser |
| 36 | + |
| 37 | +ℹ️ [Applicability to non-browser JS environments #62](https://github.com/w3c/machine-learning-workshop/issues/62) - @jasonmayes @phoddie @huningxin @WenheLI |
| 38 | +- ❓ Pay attention to the applicability of the browser-targeted work to non-browser JS environments, in particular Node.js. |
| 39 | +- ✔️ Proposal: Extend W3C coordination to TC53 and non-browser projects. |
| 40 | + |
| 41 | +ℹ️ [Targeting WASI-NN and WebNN together #96](https://github.com/w3c/machine-learning-workshop/issues/96) - @mehmetoguzderin @mingqiusun @abrown |
| 42 | +- ❓ Should libraries for browsers and/or Wasm execution environments be able to target WebNN and WASI-NN together? |
| 43 | +- ✔️ Proposal: TBD |
| 44 | + |
| 45 | +## Considerations for creating and deploying models |
| 46 | + |
| 47 | +ℹ️ [Protecting ML models #67](https://github.com/w3c/machine-learning-workshop/issues/67) - @jasonmayes @tidoust @pyu10055 @jbingham |
| 48 | +- ❓ Some ML providers need to ensure their ML models cannot be extracted from a browser app. |
| 49 | +- ✔️ Proposal: Investigate existing access control mechanisms for video, learnings from 3D assets. |
| 50 | + |
| 51 | +ℹ️ [ML model format #74](https://github.com/w3c/machine-learning-workshop/issues/74) - @cynthia @jbingham @wchao1115 |
| 52 | +- ❓ There is no standard format for packaging and shipping ML models, model formats evolve rapidly. |
| 53 | +- ✔️ Proposal: Initially focus on defining a Web API for accelerating established reusable ML operations instead of standardizing a model format. |
| 54 | + |
| 55 | +ℹ️ [In-browser training #82](https://github.com/w3c/machine-learning-workshop/issues/82) and [Training across devices #83](https://github.com/w3c/machine-learning-workshop/issues/83) - @irealva @cynthia |
| 56 | +- ❓ The current in-browser efforts are focused on inference rather than training. |
| 57 | +- ✔️ 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. |
| 58 | + |
| 59 | +## September 22, 2020, 2pm UTC [🗓️](https://www.timeanddate.com/worldclock/fixedtime.html?iso=20200922T14) |
| 60 | + |
| 61 | +>🔎 **Scope:** Web Platform Foundations for Machine Learning |
| 62 | +> |
| 63 | +>✅ **Goal:** Understand how machine learning fits into the Web technology stack |
| 64 | +
|
| 65 | +- [💡 "Web Platform Foundations" discussion topics](https://github.com/w3c/machine-learning-workshop/issues?q=is%3Aissue+is%3Aopen+label%3A%22Web+Platform+Foundations%22+sort%3Acomments-desc) |
| 66 | + |
| 67 | +## September 23, 2020, 2pm UTC [🗓️](https://www.timeanddate.com/worldclock/fixedtime.html?iso=20200923T14) |
| 68 | + |
| 69 | +>🔎 **Scope:** Machine Learning Experiences on the Web: A **Developer’s** Perspective |
| 70 | +> |
| 71 | +>✅ **Goal:** Authoring ML experiences on the Web; challenges and opportunities of reusing existing ML models on the Web; on-device training, known technical solutions, gaps |
| 72 | +
|
| 73 | +- [💡 "Developer's Perspective" discussion topics](https://github.com/w3c/machine-learning-workshop/issues?q=is%3Aissue+is%3Aopen+label%3A%22Developer%27s+Perspective%22+sort%3Acomments-desc) |
| 74 | + |
| 75 | +## September 29, 2020, 2pm UTC [🗓️](https://www.timeanddate.com/worldclock/fixedtime.html?iso=20200929T14) |
| 76 | + |
| 77 | +>🔎 **Scope:** Machine Learning Experiences on the Web: A **User’s** Perspective |
| 78 | +> |
| 79 | +>✅ **Goal:** Web & ML for all: education, learning, accessibility, cross-industry experiences, cross-disciplinary ML: music, art, and media meet ML; Share learnings and best practices across industries |
| 80 | +
|
| 81 | +- [💡 "User's Perspective" discussion topics](https://github.com/w3c/machine-learning-workshop/issues?q=is%3Aissue+is%3Aopen+label%3A%22User%27s+Perspective%22+sort%3Acomments-desc) |
| 82 | +- 👍 Conclusions & Next Steps |
| 83 | + |
| 84 | + |
| 85 | +[header]: https://www.w3.org/comm/assets/graphics/web-ML/workshop-bg.png "W3C Workshop on Web and Machine Learning header" |
0 commit comments