（中 文）人工智能导论

Teacher

Andrew Beng Jin Teoh

First day of classes

7 July 2025

Last day of classes

17 July 2025

Course Credit

2

Course   Description

Course Introduction

Artificial Intelligence is one of the   fastest-growing and most exciting fields lately, and machine learning   represents its genuine bleeding edge. This course covers several traditional   and deep learning models, e.g. linear and non-linear regression, logistic   regression, Bayesian classifiers, principal component analysis, clustering,   multilayer perceptron and convolutional neural networks. Methods to train and   optimize the learning models and to perform effective inference will be   highlighted. The course will cover the underlying theory and the range of   applications to which machine learning has been applied.

Objective

1. Students will be able   to learn several conventional and deep learning models.

2. Students will be able   to learn how to apply machine learning methods for classification, feature   extraction and regression.

Assignments (essay or other forms)

Quizzes and Final Project

Text Books and Reading Materials

1. Deep Learning/Goodfellow, Ian/MIT Press/2017

2. Dive into Deep Learning,  

3. Artificial   Intelligence: A Modern Approach

Faculty：Andrew   Beng Jin Teoh

Targeted Student：Undergraduate   Students

Course Credit：2

Lecture Hours：32 Theoretical   Hours

Course Leader：

Name：Andrew   Beng Jin Teoh

E-mail: bjteoh@yonsei.ac.kr

Office：

Mobile:

Course Staff：

Name：Huai Yu

E-mail: yuhuai@whu.edu.cn

Office：

Mobile:

Course Type：专业必修课Compulsory   Specialty Course

Related Preview Courses：

Calculus, Probability Theory and   Linear Algebra

Introduction   to AI and Machine Learning

2

Regression   Problems and Least Square Estimation

3

Logistic   Regression and Maximum Likelihood Estimation

3

Support   Vector Machine and Kernel Functions

3

Principal   Component Analysis

3

Data   Clustering

2

Neural   Networks (Multilayer Perceptron)

3

Backpropagation   Algorithm

2

Introduction   to Deep Learning

2

Convolutional   Neural Networks

3

Transfer   Learning

3

Machine   Learning Fever, Criticism and Wrap up.

3