LLM 101: Foundations and
Practical Application
This page:
https://ewh.ieee.org/r2/baltimore/continuing_education/Web_Ad_LLM_101_2025.htm
This is an in-person course.
|
|
The Baltimore Section of the IEEE is organizing and
sponsoring a series of online and in-person courses for group or individual
participation, all eligible for CEU credits. The next course is planned for
Oct 25, 2025. The Baltimore Section of the IEEE extends this invitation
also to members of neighboring IEEE sections, who can participate under the
same conditions. |
|
Date: |
Nov 1, 2025 (Saturday) |
|
|
Start time: |
10:00 am (please arrive by 9:45 am) |
|
|
End time: |
2:00 pm |
|
|
Location: |
Room ILSB 233 Interdisciplinary Life Sciences
Building at UMBC
University
of Maryland, Baltimore County 1000 Hilltop
Circle, Baltimore, MD 21250 |
|
Course Provider: Educational
Activities, Baltimore Section of the IEEE
Credits: 0.4 CEU / 4 PDH
Course
Program Length: 4 hours
Course Program
Description
Audience
- Basic understanding of python, AI/ML
Total
Duration: 4.0 Hours
Part 1: Theoretical Foundations (1.5 Hours)
1. Introduction to Large Language Models (30 minutes)
- Topics Covered:
- Evolution from AI to Generative AI
- Understanding Neural Networks and Transformers
- Overview of Foundation Models (e.g., GPT, Claude,
Gemini)
- Learning
Outcome: Grasp the basic architecture
and functioning of LLMs.
2. Prompt Engineering Techniques (30 minutes)
- Topics Covered:
- Crafting Effective Prompts
- Zero-shot and Few-shot Learning
- Chain-of-Thought and ReAct
Techniques
- Learning
Outcome: Develop skills to interact
effectively with LLMs through prompt design.
3. Retrieval-Augmented Generation (RAG) Concepts (30 minutes)
- Topics Covered:
- Introduction to RAG and its Importance
- Components: Retrieval Mechanism and Generation Model
- Use Cases and Benefits
- Learning
Outcome: Understand how RAG enhances
LLM capabilities by integrating external knowledge.
Part 2: Hands-On Application in Google Colab (2.5 Hours)
1. Setting Up the Environment (30 minutes)
- Activities:
- Accessing Google Colab
- Installing Necessary Libraries (e.g., LangChain, FAISS)
- Loading Sample Data (e.g., PDF documents)
- Learning
Outcome: Prepare the workspace for
building a RAG application.
2. Building a RAG Pipeline (60 minutes)
- Activities:
- Text Extraction and Chunking
- Creating Embeddings and Storing in Vector Database
- Implementing Retrieval Mechanism
- Integrating with a Language Model for Response
Generation
- Learning
Outcome: Construct a functional RAG
system capable of answering queries based on provided documents.
3. Enhancing the RAG Application (30 minutes)
- Activities:
- Implementing Reranking Techniques (e.g., BM25)
- Testing with Various Queries
- Discussing Potential Improvements and Extensions
- Learning
Outcome: Refine the RAG system for
better accuracy and explore avenues for further development.
4. Q&A and Discussion (30 minutes)
- Activities:
- Addressing Participant Questions
- Sharing Best Practices
- Discussing Real-World Applications
- Learning
Outcome: Consolidate learning and
clarify any doubts regarding LLMs and RAG.
Important:
Course attendees are welcome to bring their own laptops for
the hands-on activities during Part 2 of this course.
There will be a short lunch break (pizza provided) for
questions and networking
On-campus
parking on Saturdays is free of charge. You can park in the nearby Commons
Garage.
Upon successful completion of this course program, you are eligible to receive a digital certificate in PDF format that can be shared on LinkedIn and other social networks (please see below):
Who
Should Attend: Computer engineers, data scientists, data
engineers, software developers, business executives, industry
executives, industry leaders, business leaders, technical managers, and
similar professionals.
Instructor
Dr.
Swati
Tyagi is a seasoned AI/ML
professional with deep expertise in generative AI, large language models
(LLMs), and responsible AI. She holds a Ph.D.
in Financial Services Analytics with a specialization in
Machine Learning from the University
of Delaware, a Masters
in Technology Management from IITD, and a Bachelors in Computer Science and
Engineering.
Swati has led high-impact AI initiatives
across the finance, healthcare, and education sectors. In her current role as a
Senior Machine Learning
Engineer at JPMorgan Chase, she focuses on delivering scalable
and ethical AI solutions.
Her expertise spans large-scale
model deployment, explainability, bias mitigation,
and hyper-personalization. Swati blends advanced technical skills in AI/ML with
practical experience in MLOps, cloud-native architectures (AWS),
and production-grade
system development. She also serves in advisory roles, offering
strategic guidance to LLM startups and AI education programs.
An active contributor to the
global AI community, Swati serves on technical program committees, editorial
boards, and advisory panels. She is an IEEE
Senior Member and a dedicated lifelong learner, committed to
shaping the future of responsible AI through cutting-edge research, mentorship,
and community engagement.
Course registration FEES (to be paid through vTools upon registration):
The
Baltimore Section of the IEEE provides the main support for this course. We
expect attendees to cover the following minimal costs at vTools
during registration:
|
|
Colleague
pays at registration |
|
All IEEE members (incl. student members) |
$10.00 |
|
Non-members of the IEEE |
$50.00 |
The course is eligible for 0.4 CEUs equivalent to 4
PDHs. Upon successful completion and completing the evaluation form,
participants will be eligible to receive a digital certificate at no additional cost.
https://events.vtools.ieee.org/m/492735
Important: We will need each participant's name and email address. Please provide only one email address!
For more information email
to: bgramat-at-jhmi.edu