WebML WG Teleconference – 21 March 2024 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md



WebML WG Teleconference – 21 March 2024 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#webml-wg-teleconference--21-march-2024---1500-1600-utc>

⏰ This is a semi-annual reminder of the upcoming Daylight Saving Time (DST) change<https://www.timeanddate.com/time/dst/2024a.html>. Please note the adjusted time for the locations annotated with "⏰ adjusted for DST".

See the timezone table ...
San Francisco (U.S.A. - California)     Thu, 21 March 2024      08:00   UTC-7 hours (⏰ adjusted for DST)
Boston (U.S.A. - Massachusetts) Thu, 21 March 2024      11:00   UTC-4 hours (⏰ adjusted for DST)
London (United Kingdom - England)       Thu, 21 March 2024      15:00   UTC+0 hours
Berlin (Germany)        Thu, 21 March 2024      16:00   UTC+1 hours
Helsinki (Finland)      Thu, 21 March 2024      17:00   UTC+2 hours
Shanghai (China)        Thu, 21 March 2024      23:00   UTC+8 hours
Tokyo (Japan)   Fri, 22 March 2024      00:00   UTC+9 hours
Corresponding UTC (GMT) Thu, 21 March 2024      15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20240321T15


Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#logistics>

  *   Chair: Anssi
  *   Scribe: ? (see howto<https://github.com/webmachinelearning/meetings/blob/main/scribe-howto.md>, volunteers welcome!)
  *   IRC: irc://irc.w3.org:6667/#webmachinelearning

  *   IRC web client: https://irc.w3.org/?channels=#webmachinelearning

  *   Joining instructions: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2023Jun/0000.html

  *   Minutes: https://www.w3.org/2024/03/21-webmachinelearning-minutes.html


Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#agenda>
ℹ️ Understanding and managing the impact of ML models on the Web
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#%E2%84%B9%EF%B8%8F-understanding-and-managing-the-impact-of-ml-models-on-the-web>

The W3C Team has documented its shared understanding of the current and expected systemic impact of AI and ML models in particular on the Web. We'll hear an introduction to this work that references and in part builds upon this group's efforts including WebNN API, Ethical Principles for Web Machine Learning, Hybrid AI exploration, and more.

  *   ☰ Understanding and managing the impact of ML models on the Web https://www.w3.org/reports/ai-web-impact/

  *   ⨀ Comments welcome via GitHub issues https://github.com/w3c/ai-web-impact/issues


ℹ️ MLBuffer update
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#%E2%84%B9%EF%B8%8F-mlbuffer-update>

Update to the group on the latest developments in the MLBuffer exploration, learnings from the implementation. Spec design discussion to resume informed by the implementation findings.

  *   ⨀ MLBuffer proposal webmachinelearning/webnn#482<https://github.com/webmachinelearning/webnn/issues/482>
  *   ⛙ MLBuffer exploration doc webmachinelearning/webnn#541<https://github.com/webmachinelearning/webnn/pull/541>
  *   ⛭ Chromium implementation https://chromium-review.googlesource.com/c/chromium/src/+/5173676


See also:

  *   ⛭ WPT for MLBuffer creation/destroy web-platform-tests/wpt#44388<https://github.com/web-platform-tests/wpt/pull/44388>
  *   ⨀ Creation and representing MLBuffer on XPU devices webmachinelearning/webnn#542<https://github.com/webmachinelearning/webnn/issues/542>
  *   ⨀ Uploading/downloading tensor data webmachinelearning/webnn#543<https://github.com/webmachinelearning/webnn/issues/543>
  *   ⨀ Support for MLBuffer in graph execution webmachinelearning/webnn#544<https://github.com/webmachinelearning/webnn/issues/544>

ℹ️ Open issues and PRs
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#%E2%84%B9%EF%B8%8F-open-issues-and-prs>

Discuss open issues and review PRs based on your feedback:

  *   ⨀ All open issues<https://github.com/webmachinelearning/webnn/issues>
  *   ⛙ All pull requests<https://github.com/webmachinelearning/webnn/pulls>

A curated shortlist of recently discussed issues. If any are addressed prior to the meeting, we'll debrief the group on the changes to keep everyone up to date with significant developments.

Please refer to the triage guidance<https://github.com/webmachinelearning/webnn/blob/main/docs/IssueTriage.md> for more context.

🏷️ bug<https://github.com/webmachinelearning/webnn/labels/bug>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#%EF%B8%8F-bug>

  *   Define build() steps more rigorously

     *   ⨀ webmachinelearning/webnn#448<https://github.com/webmachinelearning/webnn/issues/448>, webmachinelearning/webnn#457<https://github.com/webmachinelearning/webnn/issues/457>, webmachinelearning/webnn#552<https://github.com/webmachinelearning/webnn/issues/552>
     *   ⛙ webmachinelearning/webnn#603<https://github.com/webmachinelearning/webnn/pull/603>
     *   ☰ Review PR
  *   Synchronously validate input operands/activations

     *   ⨀ webmachinelearning/webnn#572<https://github.com/webmachinelearning/webnn/issues/572>
     *   ☰ Discuss remaining work

🏷️ question<https://github.com/webmachinelearning/webnn/labels/question>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#%EF%B8%8F-question>

  *   Core operator set

     *   ⨀ webmachinelearning/webnn#573<https://github.com/webmachinelearning/webnn/issues/573>
     *   ☰ Discuss and review any additional contributions received
  *   Consider adopting new broadcasting rules

     *   ⨀ webmachinelearning/webnn#590<https://github.com/webmachinelearning/webnn/issues/590>
     *   ☰ Review the proposed options for broadcasting rules: 1) NumPy's 2) XLA's 3) keep current 4) adjust current
  *   Is "validate graph resources" backwards?

     *   ⨀ webmachinelearning/webnn#602<https://github.com/webmachinelearning/webnn/issues/602>
     *   ☰ Discuss the two options presented: 1) invert the test 2) make the test reflexive

🏷️ feature request<https://github.com/webmachinelearning/webnn/labels/feature%20request>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#%EF%B8%8F-feature-request>

  *   Consider using label to allow better error handling for async errors
     *   ⨀ webmachinelearning/webnn#585<https://github.com/webmachinelearning/webnn/issues/585>
     *   ☰ Proposed idea received support, agree on the details of the solution

🏷️ conventions<https://github.com/webmachinelearning/webnn/labels/conventions>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2024-03-21-wg-agenda.md#%EF%B8%8F-conventions>

  *   Rename inputSize variables as inputRank in algorithms

     *   ⨀ webmachinelearning/webnn#588<https://github.com/webmachinelearning/webnn/issues/588>
     *   ☰ Naming proposal to remove ambiguity, comments welcome, PR expected
  *   Consider alternate styling/linking for method argument definitions

     *   ⨀ webmachinelearning/webnn#574<https://github.com/webmachinelearning/webnn/issues/574>
     *   ☰ Globally applied styling proposal welcomes feedback, three options illustrated