2020 Exercises in fundamentals of artificial intelligence

Font size  SML

Register update notification mail Add to favorite lecture list
Academic unit or major
School of Computing
Instructor(s)
Yu Jaehoon  Chang Yuyuan  Shinyama Yusuke  Sekijima Masakazu  Yanagisawa Keisuke  Nitta Katsumi 
Course component(s)
Exercise     
Day/Period(Room No.)
Fri7-8(Zoom)  
Group
-
Course number
XCO.T490
Credits
1
Academic year
2020
Offered quarter
4Q
Syllabus updated
2020/9/29
Lecture notes updated
-
Language used
Japanese
Access Index

Course description and aims

Artificial Intelligence is a research area that aims at artificially creating intelligence like humans. In recent years, artificial intelligence was successfully applied to various domains with the advances on machine learning and deep learning utilizing big data and computation power. This lecture expects students to acquire skills that is essential for creating applications of artificial intelligence, implementing basic concepts and theories as a computer program.

Student learning outcomes

Students will be able to acquire skills that is essential for creating applications of artificial intelligence, experiencing data processing and machine learning on computers.

Keywords

classification, regression, gradient-based method, perceptron, activation function, backpropagation, automatic differentiation, convolutional neural network

Competencies that will be developed

Specialist skills Intercultural skills Communication skills Critical thinking skills Practical and/or problem-solving skills

Class flow

In class, students are required to solve excercises that are linked with the contents of taught course "XCO.T487 Fundamentals of data science".

Course schedule/Required learning

  Course schedule Required learning
Class 1 Class guidance and setup of computing environment Artificial Intelligence applied to the real world
Class 2 Essential Mathematics for Machine Learning Linear Algebra, Probability Theory and Statistics, Calculus
Class 3 Linear Regression Loss function, empirical risk minimization, overfitting,regularization,bias and variance,linear model (regression),ridge regression
Class 4 Linear Classification Linear model (classification),logistic regression, gradient methods
Class 5 Single-layer Neural Network single-layer perceptron, activation functions, computational graph, automatic differentiation
Class 6 Multi-layer Neural Network multi-layer perceptron, hidden units, backpropagation, softmax function
Class 7 Convolutional Neural Network convolutional neural network, dropout
Class 8 Discussion

Out-of-Class Study Time (Preparation and Review)

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.

Textbook(s)

None

Reference books, course materials, etc.

Cource materials are distributed via OCW-i.

Assessment criteria and methods

Based on reports for given assignments.

Related courses

  • XCO.T489 : Fundamentals of artificial intelligence
  • XCO.T483 : Advanced Artificial Intelligence and Data Science A
  • XCO.T484 : FinTech and Data Science
  • XCO.T485 : Advanced Artificial Intelligence and Data Science C
  • XCO.T486 : Advanced Artificial Intelligence and Data Science D
  • XCO.T487 : Fundamentals of data science
  • XCO.T488 : Exercises in fundamentals of data science

Prerequisites (i.e., required knowledge, skills, courses, etc.)

When you apply this exercise, take "XCO.T489 Fundamentals of artificial intelligence", "XCO.T487 Fundamentals of data science" and "XCO.T488 Exercises in fundamentals of data science" of the same quarter of the same year in parallel. When there are many applicants, a lottery may be held. In the case of students of Tokyo Tech Academy for Convergence of Materials and Informatics, take “TCM.A404 Materials Informatics” instead of “XCO.T487 Fundamentals of data science” and “XCO.T488 Exercises in fundamentals of data science.

Other

Exercises are carried out using Google Colaboratory. Students are required to get Google accounts and to get ready for using "file upload/download" in Google Drive.

Page Top