https://ontologforum.com/index.php?title=ConferenceCall_2019_04_10&feed=atom&action=historyConferenceCall 2019 04 10 - Revision history2024-03-28T09:48:06ZRevision history for this page on the wikiMediaWiki 1.39.0https://ontologforum.com/index.php?title=ConferenceCall_2019_04_10&diff=3720&oldid=previmported>KennethBaclawski: /* Proceedings */2019-05-17T17:10:00Z<p><span dir="auto"><span class="autocomment">Proceedings</span></span></p>
<p><b>New page</b></p><div>{| class="wikitable" style="float:right; margin-left: 10px;" border="1" cellpadding="10"<br />
|-<br />
! scope="row" | Session<br />
| [[session::Explainable AI]]<br />
|-<br />
! scope="row" | Duration<br />
| [[duration::1 hour]]<br />
|-<br />
! scope="row" rowspan="3" | Date/Time<br />
| [[has date::Apr 10 2019 16:00 GMT]]<br />
|-<br />
| 9:00am PDT/12:00pm EDT<br />
|-<br />
| 5:00pm BST/6:00pm CEST<br />
|-<br />
! scope="row" | Convener<br />
| [[convener::ToddSchneider|Todd Schneider]]<br />
|}<br />
<br />
= [[OntologySummit2019|Ontology Summit 2019]] XAI Session 3 =<br />
<br />
== Agenda ==<br />
<br />
* Prof. Sargur Srihari<br />
** SUNY Distinguished Professor in the Department of Computer Science and Engineering at the University at Buffalo<br />
** "Explainable Artificial Intelligence: The Probabilistic Approach"<br />
*** [http://bit.ly/2UlmgES Slides]<br />
*** [http://bit.ly/2UpAZ1x Video Recording]<br />
** Bio: https://cedar.buffalo.edu/~srihari/<br />
<br />
== Conference Call Information ==<br />
* Date: '''Wednesday, 10-April-2019''' <br />
* Start Time: 9:00am PDT / 12:00pm EDT / 6:00pm CEST / 5:00pm BST / 1600 UTC <br />
** ref: [http://www.timeanddate.com/worldclock/fixedtime.html?month=04&day=10&year=2019&hour=12&min=00&sec=0&p1=179 World Clock] <br />
* Expected Call Duration: 1 hour<br />
<br />
* The Video Conference URL is https://zoom.us/j/689971575<br />
** iPhone one-tap :<br />
*** US: +16699006833,,689971575# or +16465588665,,689971575# <br />
** Telephone:<br />
*** Dial(for higher quality, dial a number based on your current location): US: +1 669 900 6833 or +1 646 558 8665 <br />
*** Meeting ID: 689 971 575<br />
*** International numbers available: https://zoom.us/u/Iuuiouo<br />
* [http://bit.ly/2MRyySS Chat Room]<br />
<br />
== Attendees ==<br />
<br />
== Proceedings ==<br />
[12:14] ToddSchneider: Ravi can you act as host. I'm not able to get microphone to work.<br />
<br />
[12:17] RaviSharma: Todd yes i will be happy thanks<br />
<br />
[12:19] ToddSchneider: Ravi, make sure to ask Sargur to send his slides to Ken (for posting on meeting page).<br />
<br />
[12:23] John Sowa: Human-level explanations are always dialogs.<br />
<br />
[12:24] John Sowa: A single Q/A is a very rare case. Follow-up questions and discussion are essential.<br />
<br />
[12:28] John Sowa: The idea of first, second, and third wave implies that one replaces another.<br />
<br />
[12:29] John Sowa: But it's more important to have a tool kit that includes *every* method in a mix & match system.<br />
<br />
[12:31] RaviSharma1: John I agree that way one can choose the wave<br />
<br />
[12:34] John Sowa: But how can an AI system learn what features are relevant?<br />
<br />
[12:34] John Sowa: The most difficult task is to build the model.<br />
<br />
[12:35] John Sowa: How can model building be automated?<br />
<br />
[12:42] John Sowa: How could any such method be applied to a driverless car?<br />
<br />
[12:43] John Sowa: When you're driving down the highway, you may have to make a decision in a split second. How do you derive the model and compute the probabilities?<br />
<br />
[12:44] RaviSharma1: Q why log, also reason for Gausian distribution?<br />
<br />
[12:44] John Sowa: I was thinking about the recent new about Seattle.<br />
<br />
[12:45] John Sowa: one mile of telephone poles fell across a highway.<br />
<br />
[12:45] John Sowa: The probability was o.ooooooooooooooooooooooooo1<br />
<br />
[12:46] John Sowa: but when it happens, you have to deal with it.<br />
<br />
[12:46] RaviSharma1: it would be detectable if size of poles are obstructions and AI should be able to brake the car<br />
<br />
[12:48] janet singer: Ravi - yes, in that case the physical obstruction could be handled as such without explanation or understanding<br />
<br />
[12:50] Ram D. Sriram: @Hari: What about the scalability of probabilistic network-based systems<br />
<br />
[12:52] RaviSharma1: Janet Yes I was only thinking of vision and radar sensors response to any obstruction, similarly other sensors to rain snow skidding<br />
<br />
[13:01] Ram D. Sriram: @Ravi: I seem to have problems speaking into the system as I am in another meeting right now. My question is "Are these probability-based models scalable?"<br />
<br />
[13:18] BobbinTeegarden: @john: holistic metaphor?<br />
<br />
[13:25] RaviSharma1: Sargur many thanks for a wonderful talk on Probabilistic XAI.<br />
<br />
== Resources ==<br />
<br />
== Previous Meetings ==<br />
{{#ask: [[Category:OntologySummit2019]] [[Category:Icom_conf_Conference]] [[has date::<<{{#show:{{PAGENAME}}|?has date}}]] |?|<br />
mainlabel=-|sort=has date |order=desc| format=ul| limit=3}}<br />
<br />
== Next Meetings ==<br />
{{#ask: [[Category:OntologySummit2019]] [[Category:Icom_conf_Conference]] [[has date::>>{{#show:{{PAGENAME}}|?has date}}]] |?|<br />
mainlabel=-|sort=has date |order=asc| format=ul| limit=3}}<br />
<br />
[[Category:OntologySummit2019]]<br />
[[Category:Icom_conf_Conference]]<br />
[[Category:Occurrence| ]]</div>imported>KennethBaclawski