BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Interpretable Machine Learning - Tameem Adel (University of Cambri
 dge)
DTSTART:20181031T170000Z
DTEND:20181031T183000Z
UID:TALK114289@talks.cam.ac.uk
CONTACT:Adrià Garriga Alonso
DESCRIPTION:How can we design AI systems that reliably act according to th
 e true intent of their users\, even as the capability of the systems incre
 ases?\n\nThis week we will read "“Towards a Rigorous Science of Interpre
 table Machine Learning”\, by Finale Doshi-Velez and Been Kim":https://ar
 xiv.org/abs/1702.08608 \; and if there’s time\, "“Challenges for Trans
 parency” by Adrian Weller":https://arxiv.org/abs/1708.01870. Dr. Tameem 
 Adel\, a researcher in the Machine Learning Group who works in interpretab
 ility\, will lead the discussion.\n\nDoshi-Velez and Kim argue that interp
 retable machine learning is helpful to verify other properties of the syst
 em\, when these properties are difficult to state formally. Verifying info
 rmal properties is likely to be a component of ensuring a system is value 
 aligned\, so it is interesting to know about this approach to the problem.
  Weller provides a counterpoint\, detailing situations where interpretabil
 ity is actually harmful\, and also challenges to actually achieving it in 
 different situations.\n\nThere will be free pizza. At 17:00\, we will star
 t reading the paper\, mostly individually. At 17:30\, the discussion leade
 r will start going through the paper\, making sure everyone understands\, 
 and encouraging discussion about its contents and implications.\n\nEven if
  you think you cannot contribute to the conversation\, you should give it 
 a try. Last year we had several people from non-computer-y backgrounds\, a
 nd others who hadn't thought about alignment before\, that ended up being 
 essential. If you have already read the paper in your own time you can com
 e in time for the discussion.\n\nA basic understanding of machine learning
  is helpful\, but detailed knowledge of the latest techniques is not requi
 red. Each session will have a brief recap of immediate necessary knowledge
 . The goal of this series is to get people to know more about the existing
  work in AI research\, and eventually contribute to the field.\n\nInvite y
 our friends to join the mailing list (https://lists.cam.ac.uk/mailman/list
 info/eng-safe-ai)\, the Facebook group (https://www.facebook.com/groups/10
 70763633063871) or the talks.cam page (https://talks.cam.ac.uk/show/index/
 80932). Details about the next meeting\, the week's topic and other events
  will be advertised in these places.\n
LOCATION: Cambridge University Engineering Department\, CBL Seminar room B
 E4-38.  See https://www.openstreetmap.org/#map=18/52.19804/0.11969
END:VEVENT
END:VCALENDAR