BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Structure in the randomness of trained recurrent neural networks -
  Omri Barak (Technion\, Israel Institute of Technology)
DTSTART:20191114T110000Z
DTEND:20191114T120000Z
UID:TALK134428@talks.cam.ac.uk
CONTACT:Yul Kang
DESCRIPTION:Recurrent neural networks are an important class of models for
  explaining neural computations. Recently\, there has been progress both i
 n training these networks to perform various tasks\, and in relating their
  activity to that recorded in the brain. Specifically\, these models seem 
 to capture the complexity of realistic neural responses. Despite this prog
 ress\, there are many fundamental gaps towards a theory of these networks.
  What does it mean to understand a trained network? What types of regulari
 ties should we search for? How does the network reflect the task and its e
 nvironment? I will present several examples of such regularities\, in both
  the structure and the dynamics that arise through training.
LOCATION:CBL Seminar Room (BE4-38\, http://learning.eng.cam.ac.uk/Public/D
 irections)
END:VEVENT
END:VCALENDAR