Machine Learning Theory and AI Applications - Kim Yonghee

Course Description

This course introduces core machine learning concepts and practical generative AI applications for business. Students learn supervised/unsupervised learning, prompt engineering, RAG systems, and AI agents through hands-on projects using accessible cloud tools.

Learning Objectives

Explain core concepts of machine learning and LLM-based generative AI
Apply advanced prompt engineering strategies such as chain-of-thought and few-shot
Build document-grounded RAG workflows
Design and use role-specific AI agents
Evaluate hallucination, bias, and AI ethics risks in real use cases

Evaluation

Midterm

30%

Final

30%

Assignment

10%

Project

20%

Attendance

10%

Weekly Schedule

Week	Topic	Details
1	AI, ML, and DL Overview	Relationships among AI/ML/DL and business impact
2	Understanding LLMs and Generative AI	Transformer intuition, tokenization, and context handling
3	ML Core Concepts I: Supervised Learning	Classification/regression concepts and business examples
4	ML Core Concepts II: Unsupervised Learning	Clustering, evaluation metrics, and train/test split
5	Prompt Engineering I	Prompt structure, zero-shot and few-shot patterns
6	Prompt Engineering II	Chain-of-thought and output-structure control
7	Structured Data Practice	Vibe coding workflow for classification tasks
8	Midterm Exam
9	Advanced Structured Data Practice	Regression/clustering tasks and insight extraction
10	Unstructured Data Practice	Text sentiment analysis and image classification demo
11	RAG Fundamentals and Practice	Document-grounded QA and hallucination reduction
12	AI Agent Design and Utilization	Task-specific agent setup for business workflows
13	AI Ethics and Limitations	Bias, privacy, governance, and responsible usage
14	Team Project Presentation	Applied business problem-solving project showcase
15	Final Exam

Textbook

Instructor lecture notes and lab materials