BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Colombo
BEGIN:DAYLIGHT
DTSTART:20380119T084407
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
RRULE:FREQ=YEARLY;BYDAY=3TU;BYMONTH=1
TZNAME:+0530
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20060415T000000
TZOFFSETFROM:+0600
TZOFFSETTO:+0530
RRULE:FREQ=YEARLY;BYDAY=3SA;BYMONTH=4
TZNAME:+0530
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251114T181117Z
UID:741F4CDC-BD07-4BA0-85D7-9CDBF153524F
DTSTART;TZID=Asia/Colombo:20250603T183000
DTEND;TZID=Asia/Colombo:20250603T183200
DESCRIPTION:The SLAIC Session 2 Part I\, held on May 9th\, was conducted by
  Ms. Ishani Udeshika\, a Data Scientist at Zone24x7. She delivered an insi
 ghtful introduction to Large Language Models\, breaking down their capabil
 ities as well as the limitations they face in real-world use cases\, espec
 ially when operating without current or domain-specific knowledge. To addr
 ess this challenge\, she introduced the concept of Retrieval-Augmented Gen
 eration (RAG)\, a powerful technique that enhances LLM performance by comb
 ining them with external\, retrievable knowledge. Her session offered a ba
 lanced mix of theoretical background and practical insight\, including a b
 rief demonstration of how RAG functions in real scenarios. Participants we
 re highly engaged\, with an interactive Q&A segment allowing them to ask q
 uestions and gain a deeper understanding of the topic.\n\nSpeaker(s): Hans
 a Perera\, \n\nVirtual: https://events.vtools.ieee.org/m/514795
LOCATION:Virtual: https://events.vtools.ieee.org/m/514795
ORGANIZER:ieeeypsl@gmail.com
SEQUENCE:15
SUMMARY:SLAIC Session 1- Introduction to Generative AI & Prompt Engineering
URL;VALUE=URI:https://events.vtools.ieee.org/m/514795
X-ALT-DESC:Description: <br /><p><span data-sheets-root="1">The SLAIC Sessi
 on 2 Part I\, held on May 9th\, was conducted by Ms. Ishani Udeshika\, a D
 ata Scientist at Zone24x7. She delivered an insightful introduction to Lar
 ge Language Models\, breaking down their capabilities as well as the limit
 ations they face in real-world use cases\, especially when operating witho
 ut current or domain-specific knowledge. To address this challenge\, she i
 ntroduced the concept of Retrieval-Augmented Generation (RAG)\, a powerful
  technique that enhances LLM performance by combining them with external\,
  retrievable knowledge. Her session offered a balanced mix of theoretical 
 background and practical insight\, including a brief demonstration of how 
 RAG functions in real scenarios. Participants were highly engaged\, with a
 n interactive Q&amp\;A segment allowing them to ask questions and gain a d
 eeper understanding of the topic. <br></span></p>
END:VEVENT
END:VCALENDAR