From OntologPSMW

Jump to: navigation, search
[ ]
    (1)
Session Explainable AI
Duration 1 hour60 minute
3,600 second
0.0417 day
Date/Time Apr 10 2019 16:00 GMT
9:00am PDT/12:00pm EDT
5:00pm BST/6:00pm CEST
Convener Todd Schneider

Contents

Agenda     (2A)

Conference Call Information     (2B)

Attendees     (2C)

Proceedings     (2D)

[12:14] ToddSchneider: Ravi can you act as host. I'm not able to get microphone to work.     (2D1)

[12:17] RaviSharma: Todd yes i will be happy thanks     (2D2)

[12:19] ToddSchneider: Ravi, make sure to ask Sargur to send his slides to Ken (for posting on meeting page).     (2D3)

[12:23] John Sowa: Human-level explanations are always dialogs.     (2D4)

[12:24] John Sowa: A single Q/A is a very rare case. Follow-up questions and discussion are essential.     (2D5)

[12:28] John Sowa: The idea of first, second, and third wave implies that one replaces another.     (2D6)

[12:29] John Sowa: But it's more important to have a tool kit that includes *every* method in a mix & match system.     (2D7)

[12:31] RaviSharma1: John I agree that way one can choose the wave     (2D8)

[12:34] John Sowa: But how can an AI system learn what features are relevant?     (2D9)

[12:34] John Sowa: The most difficult task is to build the model.     (2D10)

[12:35] John Sowa: How can model building be automated?     (2D11)

[12:42] John Sowa: How could any such method be applied to a driverless car?     (2D12)

[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?     (2D13)

[12:44] RaviSharma1: Q why log, also reason for Gausian distribution?     (2D14)

[12:44] John Sowa: I was thinking about the recent new about Seattle.     (2D15)

[12:45] John Sowa: one mile of telephone poles fell across a highway.     (2D16)

[12:45] John Sowa: The probability was o.ooooooooooooooooooooooooo1     (2D17)

[12:46] John Sowa: but when it happens, you have to deal with it.     (2D18)

[12:46] RaviSharma1: it would be detectable if size of poles are obstructions and AI should be able to brake the car     (2D19)

[12:48] janet singer: Ravi - yes, in that case the physical obstruction could be handled as such without explanation or understanding     (2D20)

[12:50] Ram D. Sriram: @Hari: What about the scalability of probabilistic network-based systems     (2D21)

[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     (2D22)

[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?"     (2D23)

[13:18] BobbinTeegarden: @john: holistic metaphor?     (2D24)

[13:25] RaviSharma1: Sargur many thanks for a wonderful talk on Probabilistic XAI.     (2D25)

Resources     (2E)

Previous Meetings     (2F)


Next Meetings     (2G)