BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20230312T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221106T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20221126T014521Z
UID:378BD7E9-0A8B-4402-A87E-A06620EBDB07
DTSTART;TZID=America/Los_Angeles:20221125T140000
DTEND;TZID=America/Los_Angeles:20221125T153000
DESCRIPTION:We investigate in detail the effects of noise on the performanc
 e of reservoir computing. We focus on an application in which reservoir co
 mputers are used to learn the relationship between different state variabl
 es of a chaotic system. We recognize that noise can affect differently the
  training and the testing phases. We find that the best performance of the
  reservoir is achieved when the strength of the noise that affects the inp
 ut signal in the training phase equals the strength of the noise that affe
 cts the input signal in the testing phase. For all the cases we examined\,
  we found that a good remedy to noise is to low-pass filter the input and 
 the training/testing signals\; this typically preserves the performance of
  the reservoir\, while reducing the undesired effects of noise.\n\nSpeaker
 (s): Prof. Francesco Sorrentino\, \n\nVirtual: https://events.vtools.ieee.
 org/m/334133
LOCATION:Virtual: https://events.vtools.ieee.org/m/334133
ORGANIZER:ljilja@cs.sfu.ca
SEQUENCE:6
SUMMARY:Reservoir Computing with Noise
URL;VALUE=URI:https://events.vtools.ieee.org/m/334133
X-ALT-DESC:Description: <br /><pre class="moz-quote-pre">We investigate in 
 detail the effects of noise on the performance of reservoir computing. We 
 focus on an application in which reservoir computers are used to learn the
  relationship between different state variables of a chaotic system. We re
 cognize that noise can affect differently the training and the testing pha
 ses. We find that the best performance of the reservoir is achieved when t
 he strength of the noise that affects the input signal in the training pha
 se equals the strength of the noise that affects the input signal in the t
 esting phase. For all the cases we examined\, we found that a good remedy 
 to noise is to low-pass filter the input and the training/testing signals\
 ; this typically preserves the performance of the reservoir\, while reduci
 ng the undesired effects of noise.</pre>
END:VEVENT
END:VCALENDAR