Print

2020　Machine Learning

Font size  SML

Register update notification mail Add to favorite lecture list
Academic unit or major
Undergraduate major in Computer Science
Instructor(s)
Okazaki Naoaki 
Class Format
Lecture    (ZOOM)
Media-enhanced courses
Day/Period(Room No.)
Tue7-8(S011)  Fri7-8(S011)  
Group
-
Course number
CSC.T254
Credits
2
Academic year
2020
Offered quarter
4Q
Syllabus updated
2020/9/18
Lecture notes updated
-
Language used
Japanese
Access Index

Course description and aims

Machine Learning is a "field of study that gives computers the ability to learn without being explicitly programmed" (Arthur Samuel, 1959). With the advances in theories and algorithms, big data, and computation power, machine learning recently showed an astonishing progress, applied to various fields other than computer science. This lecture introduces the foundamental concepts and theories of machine learning that are essential for any engineers to apply machine learning technologies. This lecture also provides exercises where students can cultivate the skill for implementing the theories and algorithm as computer programs in Python.

Student learning outcomes

* Acquire knowledge about the foundamental concepts and theories of machine learning
* Understand the theories and algorithms through implementations
* Learn the basic skill for data processing

Keywords

regression, classification, clustering, dimensionality reduction, reignforce learning

Competencies that will be developed

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

Class flow

This class consists of: lectures explaining the concepts and theories; and exercises to realize them on computers

Course schedule/Required learning

  Course schedule Required learning
Class 1 Introduction, Essentials of Python programming Introduction to machine learning, Python programming
Class 2 Data Visualization Reading/writing data, line chart, bar chart, plot, heatmap
Class 3 Linear Regression least squares method, maximum likelihood estimation, gradient method, evaluation, overfitting, regularization
Class 4 Linear Classification (1) threshold logic unit, binary classification, perceptron, logistic regression, evaluation
Class 5 Linear Classification (2) Multi-class classification, softmax function
Class 6 Exercise 1 Exercise for the classes 3-5
Class 7 Deep Neural Networks (1) activation function, computation graph, automatic diffrentiation, backpropagation
Class 8 Multilayer Neural Networks (2) convolutional neural networks, dropout, mini-batch optimization
Class 9 Support Vector Machine margin, duality, support vectors, kernel functions, multi-class classification
Class 10 Exercise 2 Exercise for the classes 7-9
Class 11 Clustering Hierarchical clustering, K-means
Class 12 Dimentionality Reduction principal component analysis, singular value decomposition, random projection
Class 13 Reignforcement Learning Markov decision process, Bellman equation, value iteration, policy iteration, Q learning
Class 14 Exercise 3 Exercise for the classes 11-13

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 on OCW-i.

Assessment criteria and methods

Based on the three reports (60%) and the final exam (40%).

Related courses

  • CSC.T242 ： Probability Theory and Statistics
  • CSC.T272 ： Artificial Intelligence
  • CSC.T243 ： Procedural Programming Fundamentals
  • CSC.T253 ： Advanced Procedural Programming
  • CSC.T352 ： Pattern Recognition
  • ART.T458 ： Advanced Machine Learning

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

None

Page Top