๐Ÿ‡ฐ๐Ÿ‡ท Korean Version

AI Introduction

This course is an Introduction to Artificial Intelligence and Machine Learning
aimed at providing a solid foundation in both classical ML and
modern deep learning.

Based on the Fundamental AI (2025, Fall) syllabus, the course walks through
Python programming, data science tools (NumPy, Pandas, Matplotlib),
feature engineering, core ML algorithms, and deep learning architectures
including MLP, CNN, and RNN, culminating in a hands-on Seq2Seq project. :contentReference[oaicite:0]{index=0}

Full weekly schedule (Syllabus): Here


๐Ÿ” Course Overview

Students will:

  • Learn the core ideas of AI and the historical development of the field
  • Understand the machine learning pipeline from data to model deployment
  • Build practical intuition for when and how to use different ML models
  • Get hands-on experience with Python + Jupyter/Colab
  • Implement and experiment with deep learning models using real datasets

๐Ÿง  Core Contents

  • Introduction to AI & Machine Learning
    • Definitions, history, and main paradigms (classical vs. neural)
  • Python for AI & ML
    • Python basics, control flow, functions
    • Jupyter/Colab workflow and quizzes
  • Data Science Programming
    • NumPy, Pandas, Matplotlib for data manipulation and visualization
  • Feature Engineering
    • Handling categorical variables, missing values
    • Normalization, standardization, and scaling
  • Classical Machine Learning Methods
    • Linear Regression, Logistic Regression
    • K-Nearest Neighbors (KNN) & K-Means
    • Decision Trees, basic evaluation metrics
  • Representation & Dimensionality Reduction
    • Principal Component Analysis (PCA)
  • Deep Learning
    • Multi-Layer Perceptron (MLP)
    • Convolutional Neural Networks (CNN)
    • Recurrent Neural Networks (RNN) & sequence modeling
    • Hands-on: RNN for Seq2Seq

๐Ÿ’ป Programming & Labs

  • Python & Jupyter/Colab-based quizzes and coding assignments
  • Step-by-step labs for:
    • Data science programming (NumPy, Pandas, Matplotlib)
    • Linear and Logistic Regression
    • KNN & K-Means
    • Deep learning experiments (MLP, CNN, RNN)
  • Emphasis on writing clean, reproducible code for ML experiments

๐ŸŽ“ Teaching Style

  • Concept-oriented lectures with visual and intuitive explanations
  • Live coding demos and notebook-based tutorials
  • Frequent quizzes and programming exercises to reinforce concepts
  • Connections to AI safety, robustness, and ethics where relevant

๐Ÿ‘จโ€๐Ÿซ Instructor

Prof. Jin Hyun Kim
Cyber Safety Lab ยท Gyeongsang National University


ํ•œ๊ตญ์–ด ๊ฐ•์˜์†Œ๊ฐœ

์ธ๊ณต์ง€๋Šฅ ์ž…๋ฌธ (Introduction to AI)

์ด ๊ณผ๋ชฉ์€ ์ธ๊ณต์ง€๋Šฅ(AI)๊ณผ ๋จธ์‹ ๋Ÿฌ๋‹(ML)์˜ ํ•ต์‹ฌ ๊ฐœ๋…์„
์ฒด๊ณ„์ ์œผ๋กœ ํ•™์Šตํ•˜๋Š” ์ž…๋ฌธยท๊ธฐ์ดˆ ๊ฐ•์˜์ž…๋‹ˆ๋‹ค.

Fundamental AI (2025, Fall) ๊ฐ•์˜๊ณ„ํš์— ๋”ฐ๋ผ,
Python ํ”„๋กœ๊ทธ๋ž˜๋ฐ๊ณผ ๋ฐ์ดํ„ฐ ๋ถ„์„ ๋„๊ตฌ(NumPy, Pandas, Matplotlib),
ํŠน์ง• ๊ณตํ•™(feature engineering), ์ „ํ†ต์ ์ธ ๋จธ์‹ ๋Ÿฌ๋‹ ์•Œ๊ณ ๋ฆฌ์ฆ˜,
๊ทธ๋ฆฌ๊ณ  MLP, CNN, RNN๊ณผ ๊ฐ™์€ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ์„ ๋‹ค๋ฃน๋‹ˆ๋‹ค.
ํ•™๊ธฐ ๋ง์—๋Š” RNN ๊ธฐ๋ฐ˜ Seq2Seq ๋ชจ๋ธ์„ ์ง์ ‘ ๊ตฌํ˜„ํ•˜๋Š” ์‹ค์Šต๊นŒ์ง€ ์ง„ํ–‰ํ•ฉ๋‹ˆ๋‹ค.

์ „์ฒด ๊ฐ•์˜ Syllabus๋Š” ๋‹ค์Œ์—์„œ ํ™•์ธํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค: Full weekly schedule (Syllabus)


๐Ÿ” ๊ฐ•์˜ ๊ฐœ์š”

ํ•™์ƒ๋“ค์€ ๋‹ค์Œ์„ ๋ชฉํ‘œ๋กœ ํ•™์Šตํ•˜๊ฒŒ ๋ฉ๋‹ˆ๋‹ค.

  • AI์˜ ๊ธฐ๋ณธ ๊ฐœ๋…๊ณผ ์—ญ์‚ฌ ์ดํ•ด
  • ๋ฐ์ดํ„ฐ์—์„œ ๋ชจ๋ธ๊นŒ์ง€ ์ด์–ด์ง€๋Š” ๋จธ์‹ ๋Ÿฌ๋‹ ์ „์ฒด ํŒŒ์ดํ”„๋ผ์ธ ์ดํ•ด
  • ์ƒํ™ฉ์— ๋งž๋Š” ML ์•Œ๊ณ ๋ฆฌ์ฆ˜ ์„ ํƒ๊ณผ ์ง๊ด€์  ์ดํ•ด
  • Python + Jupyter/Colab ํ™˜๊ฒฝ์—์„œ์˜ ์ฝ”๋”ฉ ์‹ค์Šต ๊ฒฝํ—˜
  • ์‹ค์ œ ๋ฐ์ดํ„ฐ์…‹์„ ํ™œ์šฉํ•œ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ ๊ตฌํ˜„ ๋ฐ ์‹คํ—˜

๐Ÿง  ์ฃผ์š” ํ•™์Šต ๋‚ด์šฉ

  • AI์™€ ๋จธ์‹ ๋Ÿฌ๋‹ ์†Œ๊ฐœ
    • AI์˜ ์ •์˜, ์—ญ์‚ฌ, ์ฃผ์š” ํŒจ๋Ÿฌ๋‹ค์ž„(์ „ํ†ต ML vs. ์‹ ๊ฒฝ๋ง)
  • AI๋ฅผ ์œ„ํ•œ Python ํ”„๋กœ๊ทธ๋ž˜๋ฐ
    • ํŒŒ์ด์ฌ ๊ธฐ์ดˆ ๋ฌธ๋ฒ•, ์ œ์–ด๋ฌธ, ํ•จ์ˆ˜
    • Jupyter/Colab ํ™˜๊ฒฝ์—์„œ์˜ ์‹ค์Šต ๋ฐ ํ€ด์ฆˆ
  • ๋ฐ์ดํ„ฐ ์‚ฌ์ด์–ธ์Šค ํ”„๋กœ๊ทธ๋ž˜๋ฐ
    • NumPy, Pandas, Matplotlib์„ ์ด์šฉํ•œ ๋ฐ์ดํ„ฐ ์ฒ˜๋ฆฌ์™€ ์‹œ๊ฐํ™”
  • Feature Engineering
    • ๋ฒ”์ฃผํ˜• ๋ณ€์ˆ˜ ์ธ์ฝ”๋”ฉ, ๊ฒฐ์ธก์น˜ ์ฒ˜๋ฆฌ
    • ์ •๊ทœํ™”, ํ‘œ์ค€ํ™”, ์Šค์ผ€์ผ๋ง ๊ธฐ๋ฒ•
  • ์ „ํ†ต์  ๋จธ์‹ ๋Ÿฌ๋‹ ๊ธฐ๋ฒ•
    • ์„ ํ˜• ํšŒ๊ท€(Linear Regression), ๋กœ์ง€์Šคํ‹ฑ ํšŒ๊ท€(Logistic Regression)
    • K-์ตœ๊ทผ์ ‘ ์ด์›ƒ(KNN), K-ํ‰๊ท (K-Means)
    • ์˜์‚ฌ๊ฒฐ์ •๋‚˜๋ฌด(Decision Tree), ๊ธฐ๋ณธ ํ‰๊ฐ€ ์ง€ํ‘œ
  • ํ‘œํ˜„ ํ•™์Šต & ์ฐจ์› ์ถ•์†Œ
    • ์ฃผ์„ฑ๋ถ„ ๋ถ„์„(PCA)
  • ๋”ฅ๋Ÿฌ๋‹ ๊ธฐ์ดˆ
    • ๋‹ค์ธต ํผ์…‰ํŠธ๋ก (MLP)
    • ํ•ฉ์„ฑ๊ณฑ ์‹ ๊ฒฝ๋ง(CNN)
    • ์ˆœํ™˜ ์‹ ๊ฒฝ๋ง(RNN)๊ณผ ์‹œํ€€์Šค ๋ชจ๋ธ๋ง
    • ์‹ค์Šต: RNN์„ ์ด์šฉํ•œ Seq2Seq ๋ชจ๋ธ ๊ตฌํ˜„

๐Ÿ’ป ํ”„๋กœ๊ทธ๋ž˜๋ฐ ๋ฐ ์‹ค์Šต

  • Python ๋ฐ Jupyter/Colab ํ™˜๊ฒฝ์—์„œ ์ง„ํ–‰๋˜๋Š” ํ€ด์ฆˆ์™€ ์ฝ”๋”ฉ ๊ณผ์ œ
  • ๋‹ค์Œ๊ณผ ๊ฐ™์€ ๋‹จ๊ณ„๋ณ„ ์‹ค์Šต ์ œ๊ณต:
    • ๋ฐ์ดํ„ฐ ์‚ฌ์ด์–ธ์Šค ํ”„๋กœ๊ทธ๋ž˜๋ฐ(NumPy, Pandas, Matplotlib)
    • ์„ ํ˜•/๋กœ์ง€์Šคํ‹ฑ ํšŒ๊ท€ ์‹ค์Šต
    • KNN & K-Means ํŠœํ† ๋ฆฌ์–ผ
    • MLP, CNN, RNN ๋“ฑ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ ์‹ค์Šต
  • ์žฌํ˜„ ๊ฐ€๋Šฅํ•œ ML ์‹คํ—˜ ์ฝ”๋“œ ์ž‘์„ฑ์„ ์ค‘์š”ํ•˜๊ฒŒ ๋‹ค๋ฃธ

๐ŸŽ“ ์ˆ˜์—… ๋ฐฉ์‹

  • ์ง๊ด€์ ์ธ ์˜ˆ์ œ๋ฅผ ํ†ตํ•œ ๊ฐœ๋… ์ค‘์‹ฌ ๊ฐ•์˜
  • ๋ผ์ด๋ธŒ ์ฝ”๋”ฉ๊ณผ ๋…ธํŠธ๋ถ ๊ธฐ๋ฐ˜ ํŠœํ† ๋ฆฌ์–ผ
  • ์ž์ฃผ ์ œ๊ณต๋˜๋Š” ํ€ด์ฆˆ์™€ ํ”„๋กœ๊ทธ๋ž˜๋ฐ ๊ณผ์ œ๋กœ ๊ฐœ๋… ์ •์ฐฉ
  • ํ•„์š” ์‹œ AI ์•ˆ์ „์„ฑยท๊ฒฌ๊ณ ์„ฑยท์œค๋ฆฌ ์ด์Šˆ์™€ ์—ฐ๊ฒฐํ•˜์—ฌ ๋…ผ์˜

๐Ÿ‘จโ€๐Ÿซ ๋‹ด๋‹น ๊ต์ˆ˜

๊น€์ง„ํ˜„ ๊ต์ˆ˜ (Prof. Jin Hyun Kim)
๊ฒฝ์ƒ๊ตญ๋ฆฝ๋Œ€ํ•™๊ต ์‚ฌ์ด๋ฒ„์•ˆ์ „ ์—ฐ๊ตฌ์‹ค (Cyber Safety Lab)