BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Future technology: machine learning using memristors networks - Fr
 ancesco Caravelli (LANL)
DTSTART:20170703T100000Z
DTEND:20170703T110000Z
UID:TALK73240@talks.cam.ac.uk
CONTACT:Christian Steinruecken
DESCRIPTION:I discuss the properties of general networks made of a class o
 f memristors (resistors with memory) which are used for non-conventional c
 omputing. In fact\, these components emulate the plasticity of neurons and
  can be fabricated in specialized laboratories. After having extensively i
 ntroduced these components\, we discuss a differential equation which desc
 ribes the evolution of the internal memory of a generic circuit for ideal 
 memristors. \nThis enables a formal treatment of the learning capability o
 f these circuits. I then discuss the implications of such an equation for 
 the use of memristors in machine learning\, showing that in a certain limi
 t of the parameter space the dynamics can be interpreted as a constrained 
 gradient descent. I will also give a brief account of the formal connectio
 n to Statistical Mechanics at the end.\n 
LOCATION:CBL Room BE-438\, Department of Engineering
END:VEVENT
END:VCALENDAR