BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251102T112702Z
UID:94D2D4A9-755D-42F6-840B-0E9D37032C24
DTSTART;TZID=America/New_York:20251101T093000
DTEND;TZID=America/New_York:20251101T140000
DESCRIPTION:Audience - Basic understanding of python\, AI/ML\n\nThe course 
 is eligible for 0.4 CEUs equivalent to 4 PDHs. Upon successful completion 
 and completing the evaluation form\, participants will be eligible to rece
 ive a digital certificate at no additional cost.\n\nWho Should Attend: Com
 puter engineers\, data scientists\, data engineers\, software developers\,
  business executives\, industry executives\, industry leaders\, business l
 eaders\, technical managers\, and similar professionals.\n\nCourse attende
 es are welcome to bring their own laptops for the hands-on activities duri
 ng Part 2 of this course.\n\nThere will be a short lunch break (provided) 
 for questions and networking\n\nOn-campus parking on Saturdays is free of 
 charge. You can park in the nearby Commons Garage.\n\nFurther information 
 is at:\nhttps://ewh.ieee.org/r2/baltimore/continuing_education/Web_Ad_LLM_
 101_2025.htm\n\nSpeaker(s): Swati Tyagi\, \n\nAgenda: \nRegistration 9:30 
 - 10:00\nCourse 10:00 - 2:00 PM\n\nTotal Duration: 4.0 Hours\n\nPart 1: Th
 eoretical Foundations (1.5 Hours)\n\n1. Introduction to Large Language Mod
 els (30 minutes)\n\n- Topics Covered:\n\n- Evolution from AI to Generative
  AI\n- Understanding Neural Networks and Transformers\n- Overview of Found
 ation Models (e.g.\, GPT\, Claude\, Gemini)\n- Learning Outcome: Grasp the
  basic architecture and functioning of LLMs.\n\n2. Prompt Engineering Tech
 niques (30 minutes)\n\n- Topics Covered:\n\n- Crafting Effective Prompts\n
 - Zero-shot and Few-shot Learning\n- Chain-of-Thought and ReAct Techniques
 \n- Learning Outcome: Develop skills to interact effectively with LLMs thr
 ough prompt design.\n\n3. Retrieval-Augmented Generation (RAG) Concepts (3
 0 minutes)\n\n- Topics Covered:\n\n- Introduction to RAG and its Importanc
 e\n- Components: Retrieval Mechanism and Generation Model\n- Use Cases and
  Benefits\n- Learning Outcome: Understand how RAG enhances LLM capabilitie
 s by integrating external knowledge.\n\nPart 2: Hands-On Application in Go
 ogle Colab (2.5 Hours)\n\n1. Setting Up the Environment (30 minutes)\n\n- 
 Activities:\n\n- Accessing Google Colab\n- Installing Necessary Libraries 
 (e.g.\, LangChain\, FAISS)\n- Loading Sample Data (e.g.\, PDF documents)\n
 - Learning Outcome: Prepare the workspace for building a RAG application.\
 n\n2. Building a RAG Pipeline (60 minutes)\n\n- Activities:\n\n- Text Extr
 action and Chunking\n- Creating Embeddings and Storing in Vector Database\
 n- Implementing Retrieval Mechanism\n- Integrating with a Language Model f
 or Response Generation\n- Learning Outcome: Construct a functional RAG sys
 tem capable of answering queries based on provided documents.\n\n3. Enhanc
 ing the RAG Application (30 minutes)\n\n- Activities:\n\n- Implementing Re
 ranking Techniques (e.g.\, BM25)\n- Testing with Various Queries\n- Discus
 sing Potential Improvements and Extensions\n- Learning Outcome: Refine the
  RAG system for better accuracy and explore avenues for further developmen
 t.\n\n4. Q&amp;A and Discussion (30 minutes)\n\n- Activities:\n\n- Addressing 
 Participant Questions\n- Sharing Best Practices\n- Discussing Real-World A
 pplications\n- Learning Outcome: Consolidate learning and clarify any doub
 ts regarding LLMs and RAG.\n\nRoom: 233\, Bldg: ILSB\, UMBC\, 1000 Hilltop
  Circle\, Baltimore\, Maryland\, United States\, 21250
LOCATION:Room: 233\, Bldg: ILSB\, UMBC\, 1000 Hilltop Circle\, Baltimore\, 
 Maryland\, United States\, 21250
ORGANIZER:d.herres@ieee.org
SEQUENCE:36
SUMMARY:LLM 101: Foundations and Practical Application
URL;VALUE=URI:https://events.vtools.ieee.org/m/492735
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Audience - Basic
  understanding of python\, AI/ML&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;stron
 g&gt;The course is eligible for 0.4 CEUs equivalent to 4 PDHs.&amp;nbsp\;Upon suc
 cessful completion and completing the evaluation form\, participants will 
 be eligible to receive a&amp;nbsp\;digital certificate&amp;nbsp\;at no additional 
 cost.&lt;/strong&gt;&lt;/p&gt;\n&lt;p&gt;Who Should Attend: Computer engineers\, data scient
 ists\, data engineers\, software developers\, business executives\, indust
 ry executives\, industry leaders\, business leaders\, technical managers\,
  and similar professionals.&lt;/p&gt;\n&lt;p&gt;Course attendees are welcome to bring 
 their own laptops for the hands-on activities during Part 2 of this course
 .&lt;/p&gt;\n&lt;p&gt;There will be a short lunch break (provided) for questions and n
 etworking&lt;/p&gt;\n&lt;p&gt;On-campus parking on Saturdays is free of charge. You ca
 n park in the nearby Commons Garage.&lt;/p&gt;\n&lt;p&gt;Further information is at:&lt;br
 &gt;https://ewh.ieee.org/r2/baltimore/continuing_education/Web_Ad_LLM_101_202
 5.htm&lt;/p&gt;\n&lt;p&gt;&amp;nbsp\;&lt;/p&gt;&lt;br /&gt;&lt;br /&gt;Agenda: &lt;br /&gt;&lt;p&gt;&lt;strong&gt;Registration
  9:30 - 10:00&lt;br&gt;Course 10:00 - 2:00 PM&lt;/strong&gt;&lt;/p&gt;\n&lt;h3&gt;&lt;strong&gt;Total Du
 ration:&lt;/strong&gt;&amp;nbsp\;4.0 Hours&lt;/h3&gt;\n&lt;h3&gt;&lt;strong&gt;Part 1: Theoretical Fou
 ndations (1.5 Hours)&lt;/strong&gt;&lt;/h3&gt;\n&lt;p&gt;&lt;strong&gt;1. Introduction to Large La
 nguage Models (30 minutes)&lt;/strong&gt;&lt;/p&gt;\n&lt;ul type=&quot;disc&quot;&gt;\n&lt;li class=&quot;MsoN
 ormal&quot;&gt;&lt;strong&gt;Topics Covered:&lt;/strong&gt;&lt;/li&gt;\n&lt;ul type=&quot;circle&quot;&gt;\n&lt;li clas
 s=&quot;MsoNormal&quot;&gt;Evolution from AI to Generative AI&lt;/li&gt;\n&lt;li class=&quot;MsoNorma
 l&quot;&gt;Understanding Neural Networks and Transformers&lt;/li&gt;\n&lt;li class=&quot;MsoNorm
 al&quot;&gt;Overview of Foundation Models (e.g.\, GPT\, Claude\, Gemini)&lt;/li&gt;\n&lt;/u
 l&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Learning Outcome:&lt;/strong&gt;&amp;nbsp\;Grasp t
 he basic architecture and functioning of LLMs.&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p&gt;&lt;strong&gt;2. 
 Prompt Engineering Techniques (30 minutes)&lt;/strong&gt;&lt;/p&gt;\n&lt;ul type=&quot;disc&quot;&gt;\
 n&lt;li class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Topics Covered:&lt;/strong&gt;&lt;/li&gt;\n&lt;ul type=&quot;ci
 rcle&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Crafting Effective Prompts&lt;/li&gt;\n&lt;li class=&quot;
 MsoNormal&quot;&gt;Zero-shot and Few-shot Learning&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Cha
 in-of-Thought and ReAct Techniques&lt;/li&gt;\n&lt;/ul&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;&lt;str
 ong&gt;Learning Outcome:&lt;/strong&gt;&amp;nbsp\;Develop skills to interact effectivel
 y with LLMs through prompt design.&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p&gt;&lt;strong&gt;3. Retrieval-Au
 gmented Generation (RAG) Concepts (30 minutes)&lt;/strong&gt;&lt;/p&gt;\n&lt;ul type=&quot;dis
 c&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Topics Covered:&lt;/strong&gt;&lt;/li&gt;\n&lt;ul type
 =&quot;circle&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Introduction to RAG and its Importance&lt;/
 li&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Components: Retrieval Mechanism and Generation 
 Model&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Use Cases and Benefits&lt;/li&gt;\n&lt;/ul&gt;\n&lt;li 
 class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Learning Outcome:&lt;/strong&gt;&amp;nbsp\;Understand how 
 RAG enhances LLM capabilities by integrating external knowledge.&lt;/li&gt;\n&lt;/u
 l&gt;\n&lt;h3&gt;&lt;strong&gt;&amp;nbsp\;&lt;/strong&gt;&lt;/h3&gt;\n&lt;h3&gt;&lt;strong&gt;Part 2: Hands-On Applic
 ation in Google Colab (2.5 Hours)&lt;/strong&gt;&lt;/h3&gt;\n&lt;p&gt;&lt;strong&gt;1. Setting Up 
 the Environment (30 minutes)&lt;/strong&gt;&lt;/p&gt;\n&lt;ul type=&quot;disc&quot;&gt;\n&lt;li class=&quot;Ms
 oNormal&quot;&gt;&lt;strong&gt;Activities:&lt;/strong&gt;&lt;/li&gt;\n&lt;ul type=&quot;circle&quot;&gt;\n&lt;li class=
 &quot;MsoNormal&quot;&gt;Accessing Google Colab&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Installing 
 Necessary Libraries (e.g.\, LangChain\, FAISS)&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot;
 &gt;Loading Sample Data (e.g.\, PDF documents)&lt;/li&gt;\n&lt;/ul&gt;\n&lt;li class=&quot;MsoNor
 mal&quot;&gt;&lt;strong&gt;Learning Outcome:&lt;/strong&gt;&amp;nbsp\;Prepare the workspace for bu
 ilding a RAG application.&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p&gt;&lt;strong&gt;2. Building a RAG Pipeli
 ne (60 minutes)&lt;/strong&gt;&lt;/p&gt;\n&lt;ul type=&quot;disc&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;&lt;str
 ong&gt;Activities:&lt;/strong&gt;&lt;/li&gt;\n&lt;ul type=&quot;circle&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;T
 ext Extraction and Chunking&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Creating Embedding
 s and Storing in Vector Database&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Implementing 
 Retrieval Mechanism&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Integrating with a Languag
 e Model for Response Generation&lt;/li&gt;\n&lt;/ul&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;&lt;strong
 &gt;Learning Outcome:&lt;/strong&gt;&amp;nbsp\;Construct a functional RAG system capabl
 e of answering queries based on provided documents.&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p&gt;&lt;stron
 g&gt;3. Enhancing the RAG Application (30 minutes)&lt;/strong&gt;&lt;/p&gt;\n&lt;ul type=&quot;di
 sc&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Activities:&lt;/strong&gt;&lt;/li&gt;\n&lt;ul type=&quot;c
 ircle&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Implementing Reranking Techniques (e.g.\, B
 M25)&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Testing with Various Queries&lt;/li&gt;\n&lt;li cl
 ass=&quot;MsoNormal&quot;&gt;Discussing Potential Improvements and Extensions&lt;/li&gt;\n&lt;/u
 l&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Learning Outcome:&lt;/strong&gt;&amp;nbsp\;Refine 
 the RAG system for better accuracy and explore avenues for further develop
 ment.&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p&gt;&lt;strong&gt;4. Q&amp;amp\;A and Discussion (30 minutes)&lt;/str
 ong&gt;&lt;/p&gt;\n&lt;ul type=&quot;disc&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Activities:&lt;/str
 ong&gt;&lt;/li&gt;\n&lt;ul type=&quot;circle&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Addressing Participan
 t Questions&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot;&gt;Sharing Best Practices&lt;/li&gt;\n&lt;li c
 lass=&quot;MsoNormal&quot;&gt;Discussing Real-World Applications&lt;/li&gt;\n&lt;/ul&gt;\n&lt;li class
 =&quot;MsoNormal&quot;&gt;&lt;strong&gt;Learning Outcome:&lt;/strong&gt; Consolidate learning and c
 larify any doubts regarding LLMs and RAG.&lt;/li&gt;\n&lt;/ul&gt;
END:VEVENT
END:VCALENDAR