fbpx

Course Details

Title Introduction to AI and Deep Learning Basics
Field of Study Engineering
Professor Youngjoon Won (youngjoon@hanyang.ac.kr)
Type Academic course
Delivery Type Hybrid Track (2 weeks online + 2 weeks offline): Real-time
Credits 3
Contact hours 45
Schedule Morning
Course code ISS1158
Course number 18056
Description

This course provides an introduction to the fundamental problems of artificial
intelligence and basic deep learning models used in tackling following topics:
1. AI agents and (un)informed searching algorithms
2. Machine learning techniques
3. Deep learning basics (NN, CNN, and etc.)
4. Possible group projects (in-class presentation) and take-home exam
The course outline is tentative for now. There will be some changes during the
course.

Objective

This course is designed to introduce the field of artificial intelligence and basic
deep learning techniques. Sample codes and hands-on experience will help the
student understand the theories behind the popular AI/ML techniques in practice.
Although this course is designed for all majors, there are some materials in
program languages and a little bit of math. Yet our goal is to give a friendly
introduction to all students in general.

Preparations

Should be able to write and understand texts in English.
This course is for all majors (not specific to computer-related major).
No programming experience is required, but a basic computer skill would be nice.

Materials: All materials are provided in class. Appropriate urls, tech-blogs, sample codes will be
given as we proceed.

Materials
Evaluation
Assignment
20%
Attendance
10%
Group Project
40%
Midterm
20%
Presentation
10%
Lesson Plan
Class 1: Introduction to AI and agents, examples: A quick look at Titanic survival prediction
Class 2: Understanding states and dimensions of models: Pyrobot vacuum cleaner
Class 3: Generic searching problems: 8-puzzle example
Class 4: Overview of ML, Supervised learning
Class 5: In-class presentation by group, selected publications from KDD
Class 6: Overview of ML, Supervised learning: Decision tree algorithms, entropy
Class 7: Overview of ML, Unsupervised learning: K-mean clustering
Class 8: Overview of ML, Feature extraction: Mushroom classification problem, Brightics
Class 9: Deep learning basics: Introduction to neural networks (NN)
Class 10: Deep learning basics: Gradient descent and model training/test
Class 11: Keras/Tensorflow examples: Student admission prediction
Class 12: Introduction to CNN
Class 13: AWS Sagemaker exercise (ground truth): Sound classification problem (tentative for now)
Class 14: Introduction to constrain satisfaction problem (CSP)
Class 15: Take Home Exam or Group Project Presentation
Last Updated April 15, 2021
Print
Go to Top