Fwd: WebML WG Teleconference – 10 June 2021 - 14:00-15:00 UTC+0

FYI - the first WebML WG call takes place at the usual CG slot -- all CG participants are welcome!

Begin forwarded message:

From: "Anssi Kostiainen (Intel)" <anssi.kostiainen@intel.com<mailto:anssi.kostiainen@intel.com>>
Subject: WebML WG Teleconference – 10 June 2021 - 14:00-15:00 UTC+0
Date: 3. June 2021 at 17.30.12 EEST
To: public-webmachinelearning-wg@w3.org<mailto:public-webmachinelearning-wg@w3.org>
Cc: Dominique Hazael-Massieux <dom@w3.org<mailto:dom@w3.org>>


Latest version: https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-06-10-agenda.md

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

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20210610T14


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-06-10-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/2021/06/10-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-06-10-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-06-10-agenda.md#welcome-to-the-web-machine-learning-working-group>Welcome to the Web Machine Learning Working Group

This is the first Web Machine Learning Working Group teleconference! Old and new participants alike are welcome to join.

To kick off and orientate, we'll discuss:

  *   Where we are, who we are, what are our plans for the next few months
  *   Introduction to the Web Neural Network API aka WebNN API
  *   Demystify the transition process from CG to WG, CG work adoption
  *   Collaboration model with the WebML CG and other W3C groups
  *   Meetings and TPAC vF2F
  *   Planned first key WG milestones:
     *   10 June - Start Call for Consensus to adopt the WebNN API
     *   24 June - WebNN API First Public Working Draft publication

Resources:

  *   WG home: https://www.w3.org/groups/wg/webmachinelearning

  *   Instructions for joining: https://www.w3.org/groups/wg/webmachinelearning/instructions

  *   WebNN API spec: https://webmachinelearning.github.io/webnn/

  *   WebNN API explainer: https://github.com/webmachinelearning/webnn/blob/master/explainer.md


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-06-10-agenda.md#webnn-api---new-proposals>WebNN API - new proposals

  *   Support sync API and require pre-allocated output buffers
     *   Issue: https://github.com/webmachinelearning/webnn/issues/156

     *   PR: https://github.com/webmachinelearning/webnn/pull/174

<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-06-10-agenda.md#webnn-api---tag-review>WebNN API - TAG review

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

     *   PR: WIP
  *   [tag-tracker] Ergonomics of the JS examples
     *   Issue: https://github.com/webmachinelearning/webnn/issues/139

     *   PR: WIP - pending concrete TAG feedback to inform the resolution
  *   [tag-tracker] String enum for activations
     *   Issue: https://github.com/webmachinelearning/webnn/issues/138

     *   PR: WIP - add an informative note to be incorporated into the spec to explain current design principles around activations
     *