BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:AI for Astronomy in the SKA Era - Anna Scaife (Manchester)
DTSTART:20220217T160000Z
DTEND:20220217T170000Z
UID:TALK165073@talks.cam.ac.uk
CONTACT:Clare Worley
DESCRIPTION:The expected volume of data from the new generation of scienti
 fic facilities such as the Square Kilometre Array (SKA) has motivated the 
 expanded use of semi-automatic and automatic machine learning algorithms f
 or scientific discovery in astronomy. In this field\, the robust and syste
 matic use of machine learning faces a number of specific challenges includ
 ing a paucity of labelled data for training - paradoxically\, although we 
 have too much data\, we don't have enough\, a clear understanding of the e
 ffect of biases introduced due to observational and intrinsic astrophysica
 l selection effects in the training data\, and motivating a quantitative s
 tatistical representation of outcomes from decisive AI applications. In th
 is seminar I will discuss the motivations and potential for using AI solut
 ions in astronomy\, with particular reference to radio astronomy and the S
 KA\, and how the extreme data rates of next generation instrumentation are
  driving automation in scientific analysis. I will also talk about the inh
 erent biases that AI methods can introduce\, why astronomy data may be par
 ticularly susceptible to these problems and discuss some of the potential 
 methods for quantifying\, understanding and mitigating the effect of these
  biases.
LOCATION:Hoyle Lecture Theatre (sign-up needed) + ONLINE - Details will be
  sent by email
END:VEVENT
END:VCALENDAR