Deep learning and mathematical optimization methods are becoming indispensable technologies for industry and society. These technologies are not limited to specific fields, but have general-purpose characteristics, and are expected to be applied to a wide range of fields in the future.
In this lecture, we will first understand reinforcement learning and deep reinforcement learning. At the same time, we will understand optimization methods such as mathematical programming and meta-heuristics. Finally, we will understand the characteristics of quantum computing and its technological development trends.
In this course, even beginners of machine learning and mathematical programming will be able to learn easily, and learn the principles of algorithms and the ability to implement simple methods based on the application examples of each method.
By taking this lecture, students will be able to understand and acquire the followings:
(1) Understand the development history and application scope of deep reinforcement learning.
(2) To understand the basics of mathematical programming and metaheuristics.
(3) To understand the outline of current quantum computing technology.
|✔ Applicable||How instructors' work experience benefits the course|
|The teacher in charge was conducting AI and software development at a company he started by himself. This lecture is based on the knowledge gained through practical software development.|
Deep learning, Python, programming, reinforcement learning, mathematical programming, quantum computing
|✔ Specialist skills||✔ Intercultural skills||Communication skills||Critical thinking skills||✔ Practical and/or problem-solving skills|
The class will consist mainly of lectures, with some Python programming practice, using the browser-based development environment (Google Colab).
|Course schedule||Required learning|
|Class 1||Guidance, Deep Reinforcement Learning (1)||To understand the purpose of this lecture. To understand the principles of reinforcement learning and the latest trends in value-based and strategy-based algorithms.|
|Class 2||Deep Reinforcement Learning (2) (Programming practice)||Understand the principles of game reinforcement learning through examples. Implement deep reinforcement learning in Python as an example of reinforcement learning.|
|Class 3||Overview of optimization and linear programming (1)||Understand examples of optimization and search algorithms and the concept of computational complexity classes.|
|Class 4||Linear programming (2) (programming practice)||Understand the basic principles of linear programming and perform linear programming in Python.|
|Class 5||Nonlinear Programming and Dynamic Programming||To understand nonlinear programming algorithms and dynamic programming and Dijkstra methods applied to optimal path problems.|
|Class 6||Metaheuristics||Understand meta-heuristics methods such as genetic algorithms and swarm intelligence optimization.|
|Class 7||Quantum computing||To understand the outline of quantum computing technology (quantum annealing method, quantum gate method, etc.).|
To enhance effective learning, students are encouraged to spend approximately 100 minutes preparing for class and another 100 minutes reviewing class content afterwards (including assignments) for each class.
They should do so by referring to textbooks and other course material.
Lecture materials prepared by the instructor will be used in the class.
Evaluation will be based on participation in lectures and programming practice (50%) and submission of reports (50%).