BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
DTSTART:19451014T230000
TZOFFSETFROM:+0630
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260630T060618Z
UID:F3AFCD18-0443-4005-AEF5-290FC0D76808
DTSTART;TZID=Asia/Kolkata:20260621T100000
DTEND;TZID=Asia/Kolkata:20260621T110000
DESCRIPTION:IEEE Computer Society Hyderabad Chapter\, in collaboration with
  the Industry Relations Committee of IEEE Hyderabad Section\, invites you 
 to an insightfulwebinar on:\n\n“From Numbers to Meaning: Vectors\, Embed
 dings\, and How LLMs Understand Language”\n\nSpeaker: Mr. M K Pavan Kuma
 r\nDistinguished AI Architect | GenAI &amp; RAG Expert\, Equal AI\n\nDate: 21 
 June 2026\nTime: 10:00 AM IST\nRegistration Link: https://bit.ly/CS_Webina
 r3\n\n[]\n\nAbstract:\nThis webinar explores how Large Language Models tra
 nsform language into meaningful numerical representations using vectors an
 d embeddings. Participants will gain an intuitive understanding of semanti
 c similarity\, word embeddings\, positional encoding\, and how modern LLMs
  use these concepts to understand context\, meaning\, and relationships in
  human language.\n\nJoin us to explore how vectors\, embeddings\, and LLMs
  power modern AI systems and language understanding.\n\nA great opportunit
 y for students\, researchers\, professionals\, and AI enthusiasts to deepe
 n their understanding of modern AI technologies.\n\n#IEEE #IEEECS #IEEEHyd
 erabadSection #ArtificialIntelligence #LLM #GenAI #MachineLearning #DataSc
 ience #Embeddings #RAG #AIWebinar #IEEEComputerSociety\n\nCo-sponsored by:
  INdustry Relations Committee\n\nAgenda: \nThis is high level agenda\n\nPa
 rt 1 — Vectors\n\nWhat is a vector? Intuition from geometry\nVectors in 
 high-dimensional space\nWhy vectors are useful for representing meaning\nC
 osine similarity — measuring semantic closeness\n\nPart 2 — From Words
  to Numbers\n\nThe core problem: how do machines read text?\nOne-hot encod
 ing and its limitations\nThe idea of dense representations\n\nPart 3 — E
 mbeddings\n\nWhat is an embedding?\nWord2Vec intuition (King - Man + Woman
  = Queen)\nGloVe — global co-occurrence\nContextual embeddings — why s
 tatic embeddings fall short\nBERT-style embeddings (awareness level)\n\nPa
 rt 4 — Positional Embeddings\n\nWhy position matters in language\nSinuso
 idal positional encoding (original Transformer)\nLearned positional embedd
 ings\nRoPE — intuition only\, no heavy math\n\nPart 5 — Embeddings ins
 ide LLMs\n\nToken embeddings + positional embeddings combined\nHow attenti
 on uses embeddings to build meaning\nSemantic search as a real-world appli
 cation\n\nVirtual: https://events.vtools.ieee.org/m/564282
LOCATION:Virtual: https://events.vtools.ieee.org/m/564282
ORGANIZER:maheshneerati@ieee.org
SEQUENCE:10
SUMMARY:Webinar on &quot;From Numbers to Meaning: Vectors\, Embeddings\, and How
  LLMs Understand Language&quot;
URL;VALUE=URI:https://events.vtools.ieee.org/m/564282
X-ALT-DESC:Description: &lt;br /&gt;&lt;p&gt;IEEE Computer Society Hyderabad Chapter\, 
 in collaboration with the Industry Relations Committee of IEEE Hyderabad S
 ection\, invites you to an insightfulwebinar on:&lt;br&gt;&lt;br&gt;&lt;strong&gt;&amp;ldquo\;Fr
 om Numbers to Meaning: Vectors\, Embeddings\, and How LLMs Understand Lang
 uage&amp;rdquo\;&lt;/strong&gt;&lt;br&gt;&lt;br&gt;&lt;strong&gt;Speaker: Mr. M K Pavan Kumar&lt;/strong&gt;
 &lt;br&gt;&lt;strong&gt;Distinguished AI Architect | GenAI &amp;amp\; RAG Expert\, Equal A
 I&lt;/strong&gt;&lt;br&gt;&lt;br&gt;&lt;strong&gt;Date: 21 June 2026&lt;br&gt;&lt;/strong&gt;&lt;strong&gt;Time: 10:
 00 AM IST&lt;/strong&gt;&lt;br&gt;&lt;strong&gt;Registration Link:&amp;nbsp\;&lt;a href=&quot;https://bi
 t.ly/CS_Webinar3&quot;&gt;https://bit.ly/CS_Webinar3&lt;/a&gt;&lt;/strong&gt;&lt;br&gt;&lt;br&gt;&lt;/p&gt;\n&lt;p 
 style=&quot;text-align: center\;&quot;&gt;&lt;img src=&quot;https://events.vtools.ieee.org/vtoo
 ls_ui/media/display/6f078f4e-5031-4da8-8f63-1f550e9b4499&quot; alt=&quot;&quot; width=&quot;65
 4&quot; height=&quot;817&quot;&gt;&amp;nbsp\;&lt;/p&gt;\n&lt;p&gt;&lt;br&gt;&lt;br&gt;&lt;strong&gt;Abstract:&lt;/strong&gt;&lt;br&gt;This
  webinar explores how Large Language Models transform language into meanin
 gful numerical representations using vectors and embeddings. Participants 
 will gain an intuitive understanding of semantic similarity\, word embeddi
 ngs\, positional encoding\, and how modern LLMs use these concepts to unde
 rstand context\, meaning\, and relationships in human language.&lt;br&gt;&lt;br&gt;Joi
 n us to explore how vectors\, embeddings\, and LLMs power modern AI system
 s and language understanding.&lt;br&gt;&lt;br&gt;A great opportunity for students\, re
 searchers\, professionals\, and AI enthusiasts to deepen their understandi
 ng of modern AI technologies.&lt;br&gt;&lt;br&gt;#IEEE #IEEECS #IEEEHyderabadSection #
 ArtificialIntelligence #LLM #GenAI #MachineLearning #DataScience #Embeddin
 gs #RAG #AIWebinar #IEEEComputerSociety&lt;/p&gt;&lt;br /&gt;&lt;br /&gt;Agenda: &lt;br /&gt;&lt;p&gt;Th
 is is high level agenda&lt;/p&gt;\n&lt;p&gt;Part 1 &amp;mdash\; Vectors&lt;/p&gt;\n&lt;p&gt;What is a 
 vector? Intuition from geometry&lt;br&gt;Vectors in high-dimensional space&lt;br&gt;Wh
 y vectors are useful for representing meaning&lt;br&gt;Cosine similarity &amp;mdash\
 ; measuring semantic closeness&lt;/p&gt;\n&lt;p&gt;&lt;br&gt;Part 2 &amp;mdash\; From Words to N
 umbers&lt;/p&gt;\n&lt;p&gt;The core problem: how do machines read text?&lt;br&gt;One-hot enc
 oding and its limitations&lt;br&gt;The idea of dense representations&lt;/p&gt;\n&lt;p&gt;&lt;br
 &gt;Part 3 &amp;mdash\; Embeddings&lt;/p&gt;\n&lt;p&gt;What is an embedding?&lt;br&gt;Word2Vec intu
 ition (King - Man + Woman = Queen)&lt;br&gt;GloVe &amp;mdash\; global co-occurrence&lt;
 br&gt;Contextual embeddings &amp;mdash\; why static embeddings fall short&lt;br&gt;BERT
 -style embeddings (awareness level)&lt;/p&gt;\n&lt;p&gt;&lt;br&gt;Part 4 &amp;mdash\; Positional
  Embeddings&lt;/p&gt;\n&lt;p&gt;Why position matters in language&lt;br&gt;Sinusoidal positio
 nal encoding (original Transformer)&lt;br&gt;Learned positional embeddings&lt;br&gt;Ro
 PE &amp;mdash\; intuition only\, no heavy math&lt;/p&gt;\n&lt;p&gt;&lt;br&gt;Part 5 &amp;mdash\; Emb
 eddings inside LLMs&lt;/p&gt;\n&lt;p&gt;Token embeddings + positional embeddings combi
 ned&lt;br&gt;How attention uses embeddings to build meaning&lt;br&gt;Semantic search a
 s a real-world application&lt;/p&gt;
END:VEVENT
END:VCALENDAR