WebML CG Teleconference – 23 January 2020 - 15:00-16:00 UTC+0

https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-01-23-agenda.md

San Francisco (U.S.A. - California)	07:00 PST	UTC-7 hours
Boston (U.S.A. - Massachusetts)		10:00 EST	UTC-4 hours
London (United Kingdom - England)	15:00 GMT	UTC+0 hours
Berlin (Germany)			16:00 CET	UTC+1 hours
Helsinki (Finland)			17:00 EET	UTC+2 hours
Shanghai (China)			23:00 CST	UTC+8 hours
Tokyo (Japan)				00:00 JST (Fri)	UTC+9 hours
Corresponding UTC (GMT)			15:00 UTC

### 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/2019Apr/0000.html (login with your W3C account)
* Minutes: https://www.w3.org/2020/01/23-webmachinelearning-minutes.html

### Agenda

* [investigation] buffer sharing between GPU and ML accelerator #33: update on VPU and DirectML prototyping

* conv2d #28: DirectML and ONNX input to native API mapping table

* Float16 type support #26: review PR

* Handling unsupported OperandType #36: discuss API design considerations for the failure path

* W3C Workshop on Web & Machine Learning (24-25 March 2020, Berlin): officially announced, registration open until 21 Feb 2020

For the links to the issues #NN mentioned in the agenda, please see:
https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-01-23-agenda.md

Thanks,

-Anssi (WebML CG chair)

Received on Thursday, 16 January 2020 12:00:09 UTC