WebML CG Teleconference – 29 April 2021 - 14:00-15:00 UTC+0

Latest: https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-04-29-agenda.md


WebML CG Teleconference – 29 April 2021 - 14:00-15:00 UTC+0
San Francisco (U.S.A. - California)     Thu, 29 April 2021      07:00   UTC-7 hours
Boston (U.S.A. - Massachusetts) Thu, 29 April 2021      10:00   UTC-4 hours
London (United Kingdom - England)       Thu, 29 April 2021      15:00   UTC+1 hours
Berlin (Germany)        Thu, 29 April 2021      16:00   UTC+2 hours
Helsinki (Finland)      Thu, 29 April 2021      17:00   UTC+3 hours
Shanghai (China)        Thu, 29 April 2021      22:00   UTC+8 hours
Tokyo (Japan)   Thu, 29 April 2021      23:00   UTC+9 hours
Corresponding UTC (GMT) Thu, 29 April 2021      14:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20210429T14


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-04-29-agenda.md#logistics>Logistics

  *   Chair: Anssi
  *   Scribe: ?
  *   IRC: irc://irc.w3.org:6667/#webmachinelearning

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

  *   Call-in details: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2020Apr/0000.html

  *   Minutes: https://www.w3.org/2021/04/29-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-04-29-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-04-29-agenda.md#web-machine-learning-wg-launched>Web Machine Learning WG launched

Call for Participation: Web Machine Learning Working Group: https://lists.w3.org/Archives/Public/public-webmachinelearning/2021Apr/0005.html


Blog post - W3C launched the Web Machine Learning Working Group: https://www.w3.org/blog/2021/04/w3c-launches-the-web-machine-learning-working-group/


  *   Discuss how this Community Group and the new Working Group will work together
  *   Discuss how we transition to WG and make the first formal publication of the Web Neural Network API
  *   Discuss the new deliverable working title Ethical Impact of Machine Learning on the Web

<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-04-29-agenda.md#operation-specific-apis-proposal>Operation-specific APIs proposal

Continue progress remaining features that satisfy the requirements of the operation-specific APIs proposal:

https://github.com/webmachinelearning/proposals/issues/2


  *   WebAssembly op level execution use case and resource upload and download
     *   Issue: https://github.com/webmachinelearning/webnn/issues/156

     *   Review PR: https://github.com/webmachinelearning/webnn/pull/162

  *   Clarify at which point weights are used in the compilation
     *   Issue: https://github.com/webmachinelearning/webnn/issues/157

     *   PR: WIP - discuss opens if any

<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-04-29-agenda.md#tag-review>TAG review

  *   Define a common term for logical tensor changes?
     *   Issue: https://github.com/webmachinelearning/webnn/issues/150

     *   Proposed resolution: TBD - pending TAG clarification
  *   Isomorphic JS story, worker scope exposure?
     *   Issue: https://github.com/webmachinelearning/webnn/issues/142

     *   Review PR: https://github.com/webmachinelearning/webnn/pull/163

  *   Ergonomics of the JS examples
     *   Issue: https://github.com/webmachinelearning/webnn/issues/139

     *   Resolution: Explain in the spec intro the rationale why the primary API consumer is a JS framework, note Model Loader API as a higher-level attraction targeting web developers - integrate any addition TAG comments
  *   String enum for activations
     *   Issue: https://github.com/webmachinelearning/webnn/issues/138

     *   Proposed resolution: TBD, assess pros/cons of the "failure is an option" pattern

<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-04-29-agenda.md#privacy-review>Privacy review

  *   Self-Review Questionnaire response closure

     *   Issues: https://github.com/webmachinelearning/webnn/issues/119 and https://github.com/webmachinelearning/webnn/issues/122

     *   Proposed resolution: Add Security and privacy considerations integrating informative PING feedback
     *   (All suggested normative changes have been addressed in https://github.com/webmachinelearning/webnn/pull/159)
  *   Fingerprinting via matmul

     *   Issue: https://github.com/webmachinelearning/webnn/issues/85