Breaking Black-box AI
This video is also available in the GOTO Play video app! Download it to enjoy offline access to our conference videos while on the move.
or
Machine learning and artificial intelligence are becoming wide-spread and productionalized - you no longer need a mathematics PhD and months of software development time to implement and use a machine learning algorithm. You can just call an API and you get the answer! You can treat them completely as black boxes and use them directly in your applications! But beware - all the algorithms have some cases when they fail to deliver what you're expecting. This talk is packed with live demos that show failure cases of popular algorithms, from linear regression to cutting-edge deep learning. I will look at practical examples, use standard algorithms as black boxes and observe when they fail and why.
What will the audience learn from this talk?
You will learn that although you can treat the algorithms as black boxes, they can fail silently and what to do about it.
Does it feature code examples and/or live coding?
Talk includes code examples and live coding
Prerequisite attendee experience level:
Level 200
-
Love Letter to the ComputerLinda LiukasThursday Oct 24 @ 09:15
-
Composing Bach Chorales Using Deep LearningFeynman LiangThursday Oct 24 @ 13:15
-
The Importance of LaughterAino Vonge CorryWednesday Oct 23 @ 09:15
-
Interaction Protocols: It's All About Good MannersMartin ThompsonFriday Oct 25 @ 13:30
-
Machine Learning: Alchemy for the Modern Computer ScientistErik MeijerWednesday Oct 23 @ 17:45
-
Get Ready to Rock with Sonic Pi - The Live Coding Music Synth for EveryoneSam AaronThursday Oct 24 @ 17:45
-
Welcome to a New Age of RefereeingPierluigi CollinaFriday Oct 25 @ 09:15
-
Fueling the Quantum Application Era with the CloudMurray ThomFriday Oct 25 @ 17:40
-
Extreme Digitalization in ChinaChristina BoutrupWednesday Oct 23 @ 13:15
-
Special Appearance - Why Berlin?Aimée CovoFriday Oct 25 @ 16:45