Grading성적 평가

Relative Grading상대평가 Grade distribution set by university policy.대학교 정책에 따라 성적 분포 결정.

20%Attend.출석

30%HW과제

50%Proj.프로젝트

20% Attendance출석30% Homework과제50% Project프로젝트

Schedule강의 일정

Course lecture schedule

Date	Slides	Week and topic	Homework and logistics
9/3		Week주차 1 Course intro, dev environment setup Course intro, dev environment setup	Environment setup (Python/Colab, scikit-learn, TensorFlow/Keras), diagnostic Kahoot
9/10		Week주차 2 Ch.1 – The Machine Learning Landscape Ch.1 – The Machine Learning Landscape 📖 Ch.1
9/17		Week주차 3 Ch.2 – End-to-End Machine Learning Project Ch.2 – End-to-End Machine Learning Project 📖 Ch.2	"Follow-me" full pipeline walkthrough
9/24🔴 No Class휴강	No Class Chuseok!~ No Class Chuseok!~
10/1		Week주차 4 Ch.3 – Classification Ch.3 – Classification 📖 Ch.3
10/8		Week주차 5 Ch.4 – Training Models Ch.4 – Training Models 📖 Ch.4
10/15		Week주차 6 Ch.5 – Support Vector Machines Ch.6 – Decision Trees Ch.5 – Support Vector Machines Ch.6 – Decision Trees 📖 Ch.5–6
10/22📝 Exam시험	Midterm Test 중간 퀴즈 Midterm Test 중간 퀴즈
10/29		Week주차 7 Ch.7 – Ensemble Learning & Random Forests Ch.8 – Dimensionality Reduction Ch.7 – Ensemble Learning & Random Forests Ch.8 – Dimensionality Reduction 📖 Ch.7–8	Team Project proposals due
11/5		Week주차 8 Ch.9 – Unsupervised Learning Techniques Ch.9 – Unsupervised Learning Techniques 📖 Ch.9
11/12		Week주차 9 Ch.10 – Intro to Artificial Neural Networks with Keras Ch.10 – Intro to Artificial Neural Networks with Keras 📖 Ch.10
11/19		Week주차 10 Ch.11 – Training Deep Neural Networks Ch.11 – Training Deep Neural Networks 📖 Ch.11
11/26		Week주차 11 Ch.12 – Custom Models & Training with TF Ch.13 – Loading & Preprocessing Data with TF Ch.12 – Custom Models & Training with TF Ch.13 – Loading & Preprocessing Data with TF 📖 Ch.12–13	Progress checkpoint due
12/3		Week주차 12 Ch.14 – Deep Computer Vision Using CNNs Ch.14 – Deep Computer Vision Using CNNs 📖 Ch.14
12/10		Week주차 13 Team Project Presentations Team Project Presentations	Demo + technical report due
12/17📝 Exam시험	Final Test 기말 퀴즈 Final Test 기말 퀴즈

Overview과목 소개

Prerequisites선수 과목

• Python programming; linear algebra; basic statistics 파이썬 프로그래밍; 선형대수; 기초 통계

교육목표: 지도·비지도학습 및 딥러닝 핵심 이론을 이해하고, 실제 응용(엣지 디바이스 배포 포함)에 적용할 수 있는 능력을 기름 주요내용: 통계적 학습 기초, 신경망과 딥러닝, CNN/RNN/Transformer 구조, 강화학습 개론, 엣지 디바이스(Jetson) 상 응용 실습 교수법·평가: 이론강의와 실습(Jupyter/Colab) 병행, 미니 프로젝트, 기말 발표

Course Objectives: To understand the core theories of supervised and unsupervised learning, as well as deep learning, and to develop the ability to apply them in practical applications, including deployment on edge devices. Key Topics: Statistical learning fundamentals, neural networks and deep learning, CNN/RNN/Transformer architectures, introduction to reinforcement learning, practical applications on edge devices (Jetson). Course Methodology and Assessment: The course will combine theoretical lectures with hands-on practice (using Jupyter/Colab), mini-projects, and a final presentation.

Textbooks교재

• 
  ★ Required교재

  Hands-On Machine Learning with Scikit-Learn, Keras, and Tensorflow

  Geron, Aurelien

  O'Reilly Media | 2022년 11월 15일

  Buy구매 →Amazon →

Instructor강사 소개

Aaron Snowberger

Ph.D. · Hanbat National University (2023)

✉ aaronkr.trainer @ gmail.com💬 KakaoTalk: AaronKr🌐 aaron.kr 🔬 PAI Lab →🆔 ORCID⌨ GitHub

Aaron Snowberger earned his Ph.D. in Information and Communications Engineering from Hanbat National University in South Korea in 2023. He also holds degrees in Computer Science and Media Design. He has taught technology courses for over 8 years, English for over 15 years, and has freelanced as a web developer and magazine designer for over 5 years. His current research interests include computer vision, natural language processing, image processing, signal processing, and machine learning.

Aaron Snowberger는 2023년 한국 한밭대학교에서 정보통신공학 박사 학위를 취득했습니다. 그는 또한 컴퓨터 과학 및 미디어 디자인 학위를 취득했습니다. 그는 8년 이상 기술 과정을 가르쳤고, 15년 이상 영어를 가르쳤으며, 5년 이상 웹 개발자 및 잡지 디자이너로 프리랜서로 일했습니다. 현재 연구 관심사는 컴퓨터 비전, 자연어 처리, 영상 처리, 신호 처리, 기계 학습입니다.