WebML CG Teleconference – 25 June 2020 - 14:00-15:00 UTC+0

https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-06-25-agenda.md


WebML CG Teleconference – 25 June 2020 - 14:00-15:00 UTC+0
San Francisco (U.S.A. - California)     Thu, 25 June 2020       07:00 PDT       UTC-7 hours
Boston (U.S.A. - Massachusetts) Thu, 25 June 2020       10:00 EDT       UTC-4 hours
London (United Kingdom - England)       Thu, 25 June 2020       15:00 BST       UTC+1 hours
Berlin (Germany)        Thu, 25 June 2020       16:00 CEST      UTC+2 hours
Helsinki (Finland)      Thu, 25 June 2020       17:00 EEST      UTC+3 hours
Shanghai (China)        Thu, 25 June 2020       22:00 CST       UTC+8 hours
Tokyo (Japan)   Thu, 25 June 2020       23:00 JST       UTC+9 hours
Corresponding UTC (GMT) Thu, 25 June 2020       14:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20200625T14&p1=1440


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-06-25-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, the web client has issues
  *   Minutes: https://www.w3.org/2020/06/25-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-06-25-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-06-25-agenda.md#set-inputs-and-outputs-by-string-key>Set inputs and outputs by string key

New feature to allow a graph to declare the keys of its inputs and outputs.

Review PR: https://github.com/webmachinelearning/webnn/pull/69


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-06-25-agenda.md#add-softmax-and-relevant-element-wise-binary-and-unary-ops>Add softmax and relevant element-wise binary and unary ops

Softmax required by the first-wave models.

Review PR: https://github.com/webmachinelearning/webnn/pull/68


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-06-25-agenda.md#noise-suppression>Noise suppression

Discuss next steps outlined at:

https://github.com/webmachinelearning/webnn/issues/66


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-06-25-agenda.md#webnn-api-explainer>WebNN API Explainer

Discuss and clarify the spec and explainer relationship.

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


Related: https://github.com/webmachinelearning/webnn/issues/70