2024Year 1st Semester Syllabus

Created Date 2023-12-15 15:49:14 Last-Modified 2023-12-15 15:49:14

Course
Course Title DEEP LEARNING STA3140-01
Code-Section
Credit/Time/
Experiment,Lab,Pr
3/Mon5,6/Wed6 Department Applied Statistics
actical Technique
Time
Pre-recorded lecture(Unable to take other class)
Time Mon5,6/Wed6 Location
/DWHMB101

Exam Date & Time Midterm exam Final exam

Class Language English Evaluation Type Absolute evaluation

Name Park Jaewoo Telephone

DEPARTMENT OF APPLIED Contact

Instructor's Profile Department Mail [email protected]
STATISTICS Information
Interview
Office
information

TA's Name &

Contact
Contact Name Telephone
Information
Information

This course aims to provide an introduction to deep learning. The fundamental statistical tools for neural
networks will be explored. There will also be a heavy emphasis on statistical computing (using R and
Course Description Python) and applications. Topics include generalized linear model, regularization, the learning process in
Brief Introduction of the neural networks, and various types of neural networks.
Course

Korean 딥러닝 알고리즘의 구현

1. 35%
English Implementing deep learning algorithms

Korean 딥러닝 방법론의 수리적 이해

2. 35%
English Mathematical understanding of deep learning methods

Korean 실제 데이터에 대한 딥러닝 알고리즘의 적용

Course Goals 3. 30%
English Application of deep learning algorithms to real-world data

Korean
4. 0%
English

Korean
5. 0%
English

1/4 DEPARTMENT OF INTERNATIONAL EXCHANGE JAIME RAUL

BUSTOS JR 2024-03-12 09:28:20
 The total measurable competencies must be 100%. Each course objective should set the competency as
25%. The core and major competencies should equal at least 50%.
Core Competencies
수리적분석능력 50% 융합적사고력 30% 창조적상상력 20%

Sub-Competencies/Learning
Unit1
Sub-Competencies/Learning
Unit2
Sub-Competencies/Learning
Unit3
Core Competencies(Liberal Must reflect the interrelationship between core competencies (elective courses) and major competencies
Arts)Major competency( (major studies).

Sustainable Development
Goals
Average Recommended Average Reading Average amount of
Amount of Learning per Volume writing(Based on A4)

Lecture Practice Training Presentation Dabate Team Project

Course Methods (%)
Total Amount 100
100% 0% 0% 0% 0%

PBL Subject Capstone Design CBL, Social Flipped Classroom Work

Course Methods 2 Innovation Course Experience,Internsh
Select Relevant Items

Grading Policy(%) Midterm Individual Team

Final exam Quiz Attendance Others
Total Amount 100 exam Assignment Assignment
Free Input for Other
Information 0% 20% 0% 70% 0% 10% 0%

Title of Assignment/Project Name, and Submission Type of Submission and Method

Method of Filling Out Deadline

Assignment/
Report, Project Guide

Introduction to Statistics, Statistical

Methods, Calculus, Linear Algebra, R Online Course
Prerequisite
and Python Programming, Regression Address
Analysis (or Econometrics 1).

Course Course Material Name Author Publisher Publish Year ISBN

Material

This course is designed for undergraduate students in the department of applied statistics (or for
undergraduate students who have enough knowledge about prerequisites). Students should meet
course prerequisites.
Main Learner Precautions

Attatchment

2/4 DEPARTMENT OF INTERNATIONAL EXCHANGE JAIME RAUL

BUSTOS JR 2024-03-12 09:28:20
Weekly Plan

week Period Weekly Topic & Contents Remarks

(3.2.) Spring
semester classes
2024-03-02
1 Introduction begin
2024-03-08
(3.6. - 3.8.) Course
add and drop period

2024-03-09
2 Linear Models
2024-03-15

2024-03-16
3 Logistic Regression
2024-03-22

2024-03-23
4 Regularization
2024-03-29

2024-03-30
5 Introduction to Neural Network
2024-04-05

(4.8.) First third of

2024-04-06
6 Learning Process in Neural Networks the semester ends
2024-04-12
04.10 국회의원선거

2024-04-13
7 Backpropagation
2024-04-19

(4.20. - 4.26.)
2024-04-20
8 Backpropagation Midterm
2024-04-26
Examinations
(4.29. - 5.1.) Course
withdrawal period
2024-04-27
9 Multilayer Neural Networks (5.2. - 5.3.)
2024-05-03
Application period
for S/U evaluation
(5.2. - 5.4.)
Application period
for S/U evaluation
(5.5.) Children's day
2024-05-04 (5.6.) Alternative
10 Recurrent Neural Networks
2024-05-10 holiday for Children's
Day
05.05 어린이날,
05.06 대체공휴일(어린
이날)
(5.15.) The day of
Buddha's coming,
2024-05-11
11 Convolutional Neural Networks Second third of the
2024-05-17
semester ends
05.15 부처님오신날

2024-05-18
12 Convolutional Neural Networks
2024-05-24

2024-05-25
13 Reinforcement Learning
2024-05-31

2024-06-01 (6.6.) Memorial day

14 Reinforcement Learning
2024-06-07 06.06 현충일

2024-06-08 (6.8. - 6.14.)

15 Topic Course
2024-06-14 Self-study

2024-06-15 (6.15. - 6.21.) Final

16 Final Exam
2024-06-21 Examinations

• Students with disabilities(SWDs) can request accommodations related to lectures, assignments, or tests by contacting t

3/4 DEPARTMENT OF INTERNATIONAL EXCHANGE JAIME RAUL

BUSTOS JR 2024-03-12 09:28:20
he course professor at the beginning of semester.
(However, accommodations may vary depending on the essentiality of lecture and discretion of professors.)
[Lecture]
- Visual Impairment: alternative, braille, enlarged reading materials, note-taker
- Physical Impairment: alternative reading materials, access to classroom, note-taker, assigned seat
- Hearing Impairment: note-taker/stenographer, recording lecture
- Intellectual Disability/Autism: note-taker
[Assignments and Test]
- Visual/Physical/Hearing Impairment: (reasonable) extra days for submission, alternative type of assignment, extende
d test time, alternative type of test, arranging separate test room, and proctors, test ghostwriter
- Intellectual Disability/Autism: (reasonable) extra days for submission, alternative type of assignment

4/4 DEPARTMENT OF INTERNATIONAL EXCHANGE JAIME RAUL

BUSTOS JR 2024-03-12 09:28:20