The main purpose of this course is to provide the most fundamental knowledge about AI to the students so that they can understand what the AI is. The course contains the following topics: search, planning, decision-making, and machine learning. Also, we will try to make an intelligent system. Each student should survey an interesting topic and try to make it smarter using AI techniques.
This course provides a broad introduction and fundamental knowledge about machine learning. Topics are mainly categorized into the following two parts: supervised and unsupervised learning. To understand supervised learning, we will learn linear regression, logistic regression, decision tree, SVM, and neural networks. For unsupervised learning, we will learn clustering, association rule mining, dimensionality reduction, kernel methods. The course will also perform practical machine learning projects.
Big Data System
This course provides fundamental knowledge on Big Data handling. For this, we will learn Hadoop Ecosystem tools such as HDFS, MapReduce, Hive, Spark, and Sqoop. Also, we will make a Hadoop-based system to support the analysis of big data.
Natural Language Processing
This course provides fundamental theories of natural language processing. The student will understand the different levels of morphology, part-of-speech tagging, syntax, semantics, discourse, and dialogue. Machine translation and other applications will also be introduced.
Advanced Big Data Analysis
This course provides a basic introduction to big data and corresponding quantitative research methods. The strength and limitations of big data research are discussed in depth using real-world examples. To provide hands-on experience, students will handle and analyze large, complex data structures, such as public big data and social data.