BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
DTSTART:20260329T020000
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T010000
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260809T175316Z
UID:101ADC28-2606-46FA-91C8-80248F9F2F94
DTSTART;TZID=Europe/London:20260806T173000
DTEND;TZID=Europe/London:20260806T190000
DESCRIPTION:Abstract:\n\nAI-driven data centres\, operating continuously an
 d predominantly powered by fossil fuels\, contribute significantly to glob
 al greenhouse gas emissions (2.5-3.7%). The widespread use of large founda
 tion models such as ChatGPT exacerbates this environmental impact. This ta
 lk explores strategies for mitigating AI&#39;s carbon footprint through model 
 acceleration\, aiming to significantly reduce computations while maintaini
 ng the accurate of AI models. This session will spotlight various model ac
 celeration techniques\, including Model Pruning and Quantisation\, and oth
 ers. Last\, it will outline potential future research directions in the fi
 eld of model acceleration.\n\nSpeaker(s): Guosheng \, Guosheng\n\nAgenda: 
 \n1- Welcome\n\n2- Introduction to SSIT\n\n3- Technical Talk\n\n4- Q&amp;A\n\n
 Virtual: https://events.vtools.ieee.org/m/563967
LOCATION:Virtual: https://events.vtools.ieee.org/m/563967
ORGANIZER:a.g.hessami@ieee.org
SEQUENCE:72
SUMMARY:Reduce AI’s Carbon Footprint - Accelerating Deep Learning Models
  
URL;VALUE=URI:https://events.vtools.ieee.org/m/563967
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;&lt;/p&gt;\n&lt;p class=&quot;M
 soNormal&quot;&gt;&lt;span style=&quot;mso-fareast-font-family: &#39;Times New Roman&#39;\; color:
  black\;&quot;&gt;Abstract: &lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;span style=&quot;mso-far
 east-font-family: &#39;Times New Roman&#39;\; color: black\;&quot;&gt;AI-driven data centr
 es\, operating continuously and predominantly powered by fossil fuels\, co
 ntribute significantly to global greenhouse gas emissions (2.5-3.7%). The 
 widespread use of large foundation models such as ChatGPT exacerbates this
  environmental impact. This talk explores strategies for mitigating AI&#39;s c
 arbon footprint through model acceleration\, aiming to significantly reduc
 e computations while maintaining the accurate of AI models. This session w
 ill spotlight various model acceleration techniques\, including Model Prun
 ing and Quantisation\, and others. Last\, it will outline potential future
  research directions in the field of model acceleration.&amp;nbsp\;&lt;/span&gt;&lt;/p&gt;
 \n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;span style=&quot;mso-fareast-font-family: &#39;Times New Ro
 man&#39;\; color: black\;&quot;&gt;&amp;nbsp\;&lt;/span&gt;&lt;/p&gt;&lt;br /&gt;&lt;br /&gt;Agenda: &lt;br /&gt;&lt;p&gt;&amp;nbs
 p\;&lt;/p&gt;\n&lt;p&gt;1- Welcome&amp;nbsp\;&lt;/p&gt;\n&lt;p&gt;2- Introduction to SSIT&lt;/p&gt;\n&lt;p&gt;3- T
 echnical Talk&lt;/p&gt;\n&lt;p&gt;4- Q&amp;amp\;A&amp;nbsp\;&lt;/p&gt;
END:VEVENT
END:VCALENDAR