13:44:30 RRSAgent has joined #webmachinelearning 13:44:30 logging to https://www.w3.org/2020/04/02-webmachinelearning-irc 13:45:01 Zakim has joined #webmachinelearning 13:45:05 RRSAgent, make logs public 13:45:13 Meeting: WebML CG Teleconference – 2 April 2020 13:45:21 Chair: Anssi 13:45:31 Agenda: https://github.com/webmachinelearning/meetings/blob/master/telcons/2020-04-02-agenda.md 13:45:39 Scribe: Anssi 13:45:45 scribeNick: anssik 13:46:13 Present+ Anssi_Kostiainen 13:46:26 RRSAgent, draft minutes v2 13:46:26 I have made the request to generate https://www.w3.org/2020/04/02-webmachinelearning-minutes.html anssik 13:59:58 Rama has joined #webmachinelearning 14:00:43 jonathan has joined #webmachinelearning 14:00:55 Present+ Paul_McDaniel 14:01:01 Present+ Rafael_Cintron 14:01:16 Present+ Ganesan_Ramalingam 14:01:23 Present+ Jonathan_Bingham 14:02:17 RafaelCintron has joined #webmachinelearning 14:02:43 paulmcd has joined #webmachinelearning 14:02:55 Present+ Greg_Whitworth 14:03:27 Good morning ! 14:05:32 Regrets+ Nikhil_Thorat 14:05:37 Regrets+ Daniel_Smilkov 14:09:37 [We're shuffle the agenda to match participation] 14:10:09 TOPIC: Inference API to load and run a model 14:10:32 anssik: Discuss current status and next steps (move repo to CG?), the group resolved to add the API to the group's scope. 14:10:40 -> https://github.com/jbingham/web-ml-inference Web ML Inference Explained 14:10:51 anssik: Jonathan created an issue to track the next steps, Jonathan to give a brief update? 14:11:26 jonathan: I filed an issue for the defining the plan, at this point no details yet, but have talked with folks internally familiar with the standards work and process 14:11:26 .. 14:12:56 gregwhitworth: WICG is equivalent forum to dedicated CGs like this one for incubation 14:13:24 anssik: WICG is catch-all CG, for this spec WebML CG is the right topic-specific CG 14:14:22 gregwhitworth: Jonathan is doing the right things with the incubation, have explainer available in public and accepting feedback 14:14:46 ... when it graduates, the incubation moved to a Working Group, in this case to-be-created WebML WG 14:15:00 jonathan: that sounds great 14:15:40 paulmcd has joined #webmachinelearning 14:15:46 gregwhitworth: if you like, you can create a thread in WICG Discourse and add a pointer to the WebML CG where the explainer and incubation happens 14:16:01 https://discourse.wicg.io/c/html 14:19:54 anssik: we can migrate https://github.com/jbingham/web-ml-inference to https://github.com/webmachinelearning/web-ml-inference 14:20:04 jonathan: sounds good 14:20:46 Rafael: is this API ready for prototyping at this point or for discussion? 14:22:07 jonathan: a group of Google folks are interested in looking at this, figure out who the engineers working on prototype would be 14:22:22 ... we have some ideas how to prototype this in custom Chromium build 14:22:31 ... a bit similar to what Ningxin is already doing 14:23:19 ... we'd also like to get to agreement with Microsoft on details to get backends aligned, much of the code would like in Chromium and everyone working off that codebase would share code 14:23:40 RafaelCintron: agree, that sounds like a good model, so everyone could integrate with their own backends 14:24:32 jonathan: allowing polyfilling, ONNX.js and TF Lite we may be able to do that 14:24:44 Love those . Poly fill, onnx, tflite 14:24:52 zkis has joined #webmachinelearning 14:25:06 RafaelCintron: there's no active development on ONNX.js but could use it for experimenting with this API 14:26:31 TOPIC: Virtual workshop 14:26:48 anssik: As you're aware, our in-person Web & ML workshop was postponed due to the coronavirus outbreak 14:27:09 -> https://www.w3.org/2020/01/machine-learning-workshop/ [POSTPONED] W3C Workshop on Web & Machine Learning 14:29:18 ... to overcome this situation without blocking, I've been planning with W3C's Dom a virtual workshop that'd replace the in-person workshop. Our estimate is it'd be at least 6 weeks to pull this off, so earliest it'd happen mid-May onwards. 14:30:43 anssik: First, the Program Committee would build an agenda based on its assessments of what topics would benefit to be covered. We'd use the existing in-person workshop agenda as a starting point (https://bit.ly/webml-workshop-talks). 14:31:01 anssik: The agenda would be built around 2 main modes: an offline mode and an on-line synchronous mode. 14:31:43 anssik: - an offline mode, built from pre-recorded videos of identified speakers on identified topics - ideally, reasonably short, focused talks that give a high-level of the current status on the said topic, and highlights the unsolved aspects, and the role of standardization on this. 14:32:54 anssik: - an on-line synchronous mode organized as a series of four 90 minutes video conferences spread over 4 days, at a single timeslot (optimized to allow as many of the registered participants to join), where all the (selected) participants to the virtual workshop are invited to join and participate. The said live sessions would be built over a well-defined agenda allowing to exchange on questions and topics exposed during the talks, 14:32:54 with speakers expected to participate at least in the sessions where their topics are covered. 14:33:11 anssik: Any comments on the modes: offline mode and on-line synchronous mode? Does this sound good? We need to consider timezone differences, which was a key consideration in this proposal. 14:34:22 gregwhitworth: I like the offline aspect 14:35:09 ... when reading through the in-person agenda, think we can subset the existing agenda and keep relevant topics 14:36:12 ... Web Components F2F did 2-3 hours over two days and it was very productive 14:37:24 that sounds good 14:39:47 anssik: To make this work, the following infrastructure would be provided by W3C: 14:39:58 anssik: - a platform to serve the video of the talks to a global audience 14:40:27 anssik: - a support team to inform and remind speakers of the tools, logistics and timelines to capture and upload the recorded talks 14:41:16 anssik: - a platform to host and manage the live conversation with up to 100 (or more?) participants (most likely, Zoom); optionally, the said conversation could be augmented with live audio translation of the discussions 14:41:32 anssik: - a slack instance (?) reserved to registered participants to meet & greet with other participants before, during and after the live sessions 14:41:52 anssik: To make this work, the expectation would remain that the live and interactive (slack) parts of the virtual workshop would be reserved to selected participants. To that end, interested people would be requested to apply indicating their relevant background on the topic 14:42:31 anssik: So that's the general plan, open to comments and suggestions. 14:43:31 RafaelCintron: I've found other groups using Google Meets, e.g. WebGL/GPU 14:44:01 ... could also use Microsoft Teams, makes sharing slides easy 14:45:30 RafaelCintron: WebGPU CG meetings are 7-8 people across the world, using Meets 14:46:00 anssik: we'd need a platform that can scale up to 100 participants 14:48:49 https://bit.ly/webml-workshop-talks 14:51:49 RafaelCintron: I like the concept of offline 14:52:11 ... also like the effective use of sync time where everyone has seen the offline material 14:53:09 I like the offline up front as well 14:53:30 anssik: let me start look into a subset of the agenda that would be interesting for the audience, I'll ask your feedback on that 14:55:32 TOPIC: Adjourn 14:55:45 RRSAgent, draft minutes v2 14:55:45 I have made the request to generate https://www.w3.org/2020/04/02-webmachinelearning-minutes.html anssik 14:56:08 stay safe folks !! 14:57:14 ningxin_hu has joined #webmachinelearning 14:57:46 hello ningxin! The time zones shifted today’s call 14:59:32 Chai has joined #webmachinelearning 14:59:34 hello paul! 15:00:26 sorry i missed the meeting this morning, thought it was at 8pst like last week 15:00:27 the time shift has the call starting an hour earlier now 15:00:37 London just went to daylight savings 15:01:55 sorry, i missed too, i got the time from the meeting page 15:06:11 No worries at all. We will catch the topics next time 15:08:40 ningxin_hu_ has joined #webmachinelearning 15:08:49 sounds great, thanks, have a good day 16:27:27 Zakim has left #webmachinelearning 17:36:53 zkis has joined #webmachinelearning