This course gives basic theories, methods, and algorithms of data science, data engineering, and AI to students those who have completed the course "Basics and Applications of Data Science and Artificial Intelligence I" in the first quarter. The curriculum is designed so that it provides an intermediate-level course study of data science and AI between literacy- and expert-level ones. The course would enable students to understand theories and methods deeply and achieve practical skills in problem solving through a variety of examples and exercises.
Students will be able to:
1) Understand significance of studying data science, as well as data analysis methods, and choose appropriate data analysis and visualization methods.
2) Understand roles of data engineering, representation methods of various data on a computer, and data acquisition/processing/accumulation techniques.
3) Understand history of AI, its technical background, AI ethics, machine learning and learning algorithms, neural networks and deep learning algorithms, and apply AI technology to problem solving.
Population, inferential statistics, statistical interference, statistical test, unsupervised leaning, supervised leaning, reinforcement learning, DNN, CNN, RNN, recognition, prediction
✔ Specialist skills | ✔ Intercultural skills | Communication skills | ✔ Critical thinking skills | ✔ Practical and/or problem-solving skills |
To check students’ understanding, students are assigned exercises at every class.
Course schedule | Required learning | |
---|---|---|
Class 1 | Fundamentals of mathematical statistics, part 1 | Understand basics of mathematical statistics and also learn statistical interference methods through specific examples. |
Class 2 | Fundamentals of mathematical statistics, part 2 | Learn the basic theory of hypothesis testing and understand hypothesis testing methods through specific examples. |
Class 3 | Machine learning, part 1 | Understand basics of machine learning algorithms by applying them to practical problems such as classification and clustering. |
Class 4 | Machine learning, part 2 | Understand basics of machine learning algorithms in which topics include supervised learning, cross validation, overfitting, and reinforcement learning. |
Class 5 | Neural networks and deep learning, part 1 | Understand principles of artificial neural networks and their training algorithms in which topics includes perceptron, multilayer perceptron, and back propagation algorithm. |
Class 6 | Neural networks and deep learning, part 2 | Understand structures and mechanisms of useful neural networks such as deep neural networks (DNN), convolutional neural networks (CNN), and recurrent neural networks (RNN). |
Class 7 | AI applications | Understand roles of AI technology in our daily life by looking at a wide variety of examples to which AI technology has been successfully applied. |
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.
None. Lecture materials will be given in the class.
Lecture materials will be found on T2SCHOLA in advance and shared in Zoom lecture.
Grading is based on exercises and term-end report.
Students are assumed to have the knowledge given in Calculus I and II, Linear Algebra I and II, Basics of Data Science and Artificial Intelligence, and Basics and Applications of Data Science and Artificial Intelligence I.
KOBAYASHI, Takao (lecture_ba_2023[at]dsai.titech.ac.jp)
Students can ask questions on T2SCHOLA forum or by e-mail.