BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A brain inspired electronic learning machine - Douglas Durian (Uni
 versity of Pennsylvania)
DTSTART:20230919T140000Z
DTEND:20230919T150000Z
UID:TALK205501@talks.cam.ac.uk
DESCRIPTION:Neural networks in the brain and artificial neural networks (A
 NNs) in silico are both able to learn complex functionality. While each ar
 tificial neuron is updated based on global information\, using a central p
 rocessor (CPU) and memory\, each real neuron in the brain updates itself w
 ithout external CPU. In this talk I will describe the first laboratory rea
 lization of such self-learning without use of CPU or memory.&nbsp\; Our sy
 stems consist of a network of identical variable-resistive elements that s
 elf-adjust using a local rule based on the voltage drops they experience u
 nder contrastive boundary conditions. As such\, they have many brain-like 
 advantages over ANNs and enable study of learning as a bottom-up emergent 
 process.\nCo-authors: Sam Dillavou\, Menachem Stern\, Jacob Wycoff\, Ben B
 eyer\, Marc Miskin\, Andrea Liu
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR