BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2022//speaker//XKYPBW
BEGIN:VEVENT
SUMMARY:Training Spiking Neural Networks in pure Julia - Ben Arthur\, Chri
 stopher Kim
DTSTART:20220728T173000Z
DTEND:20220728T174000Z
DTSTAMP:20260817T072654Z
UID:pretalx-juliacon-2022-UTTHUM@pretalx.com
DESCRIPTION:Training artificial neural networks to recapitulate the dynami
 cs of biological neuronal recordings has become a prominent tool to unders
 tand computations in the brain. We present an implementation of a recursiv
 e-least squares algorithm to train units in a recurrent spiking network.  
 Our code can reproduce the activity of 50\,000 neurons of a mouse performi
 ng a decision-making task in less than an hour of training time. It can sc
 ale to a million neurons on a GPU with 80 GB of memory.
LOCATION:Blue
URL:https://pretalx.com/juliacon-2022/talk/UTTHUM/
END:VEVENT
END:VCALENDAR