WebML CG Teleconference – 10 December 2020 - 15:00-16:00 UTC+0

https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md


WebML CG Teleconference – 10 December 2020 - 15:00-16:00 UTC+0
San Francisco (U.S.A. - California)     Thu, 10 December 2020   07:00   UTC-8 hours
Boston (U.S.A. - Massachusetts) Thu, 10 December 2020   10:00   UTC-5 hours
London (United Kingdom - England)       Thu, 10 December 2020   15:00   UTC+0 hours
Berlin (Germany)        Thu, 10 December 2020   16:00   UTC+1 hours
Helsinki (Finland)      Thu, 10 December 2020   17:00   UTC+2 hours
Shanghai (China)        Thu, 10 December 2020   23:00   UTC+8 hours
Tokyo (Japan)   Fri, 11 December 2020   00:00   UTC+9 hours
Corresponding UTC (GMT) Thu, 10 December 2020   15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20201210T15


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#logistics>Logistics

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

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

  *   Call-in details: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2020Apr/0000.html (login with your W3C account<https://www.w3.org/Help/Account/>) - Zoom app install<https://zoom.us/download> recommended
  *   Minutes: https://www.w3.org/2020/11/12-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#wg-charter-feedback>WG Charter feedback

Discuss a proposal to have an open-ended WG charter with a pipeline from CG to WG:

https://github.com/w3c/machine-learning-charter/issues/8


Review PR to add Tentative Specifications to the WG Charter:

https://github.com/w3c/machine-learning-charter/pull/9


Status check and discussion on the other WG Charter issues; please file any issues at:

https://github.com/w3c/machine-learning-charter/issues


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#webnn-api-tag-review-progress-report>WebNN API TAG review progress report

Submitted and TAG review team assigned, ETA by the end of 2020:

https://github.com/w3ctag/design-reviews/issues/570


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#security-and-privacy-considerations>Security and Privacy considerations

Review proposed questionnaire responses, fill in TBDs (TAG review dependency):

https://github.com/webmachinelearning/webnn/issues/119


Discuss Security and Privacy considerations for the spec:

https://github.com/webmachinelearning/webnn/issues/122


Review TAG guidelines:

https://www.w3.org/TR/security-privacy-questionnaire/#considerations


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#support-the-execution-of-the-sub-graph-scenario>Support the execution of the sub-graph scenario

Per earlier discussion major use cases addressed? Close issue?

https://github.com/webmachinelearning/webnn/issues/105


https://www.w3.org/2020/11/12-webmachinelearning-minutes.html#t03


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#support-style-transfer-models>Support style transfer models

Review PR:

https://github.com/webmachinelearning/webnn/pull/123


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#specify-the-modelbuildercreatemodel>Specify the ModelBuilder.createModel

Discuss how to clarify and specify the steps of ModelBuilder.createModel:

https://github.com/webmachinelearning/webnn/issues/107


https://webmachinelearning.github.io/webnn/#dom-modelbuilder-createmodel


E.g. concern over the topology created before the model is created.

<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#chained-api-for-the-operands>Chained API for the Operands

With no strong use case identified defer for later?

https://github.com/webmachinelearning/webnn/issues/106


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#conformance-testing-of-webnn-api>Conformance testing of WebNN API

Discuss conformance testing of operations, integration of web-platform-tests with NNAPI CTS

Review PR for generated NNAPI CTS:

https://github.com/webmachinelearning/webnn-polyfill/pull/29


Review PR for SqueezeNet model test:

https://github.com/webmachinelearning/webnn-polyfill/pull/32


Web-platform-tests framework for writing test cases:

https://web-platform-tests.org/writing-tests/testharness.html


https://web-platform-tests.org/writing-tests/idlharness.html


Background discussed at workshop:

https://github.com/w3c/machine-learning-workshop/issues/80


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-12-10-agenda.md#data-processing-proposal>Data processing proposal

Discuss proposal:

https://github.com/webmachinelearning/proposals/issues/1