Statistical Learning II

Numbering Code G-LAS12 80004 LB87 Year/Term 2021 ・ Intensive, Second semester
Number of Credits 2 Course Type Lecture
Target Year Graduate students Target Student For science students
Language Japanese and English Day/Period Intensive
February 14-16
Instructor name YAMADA RYO (Graduate School of Medicine Professor)
Outline and Purpose of the Course Days and hours (1st week of Feb, Mon, Tue, Wed)
1 February 14th 8:45-10:15
2 February 14th 10:30-12:00
3 February 14th 13:00-14:30
4 February 14th 14:45-16:15
5 February 14th 16:30-18:00
6 February 15th 8:45-10:15
7 February 15th 10:30-12:00
8 February 15th 13:00-14:30
9 February 15th 14:45-16:15
10 February 16th 16:30-18:00
11 February 16th 8:45-10:15
12 February 16th 10:30-12:00
13 February 16th 13:00-14:30
14 February 16th 14:45-16:15
15 February 16th 16:30-18:00




2021 前期 基礎B、後期 応用A
2022 前期 基礎A、後期 応用B
2023 前期 基礎B、後期 応用A
2024 前期 基礎A、後期 応用B


Data analysis methods in life science might be divided into two; (1) statistical tests and estimation and (2)
machine learning. However the distinction between them is becoming vaguer and they are fusing together
along with the change of data that get bigger and more complicated.
The topics in the Statistical Learning I and II are the methods in machine learning field. The various methods
are divided into 4 modules;
Statistical Learning Basics A
Statistical Learning Basics B
Statistical Learning Application A
Statistical Learning Application B
Basics A and B focus on the ideas of learning approaches.
Applications A and B focus on the skills of machine learning using Python.
The schedule of modules are shown below.

2021 1st semester Basics B, 2nd semester Application A
2022 1st semester Basics A, 2nd semester Application B
2023 1st semester Basics B, 2nd semester Application A
2024 1st semester Basics A, 2nd semester Application B

This semester is Application A.
Course Goals 各モジュールが扱う内容に即して、以下ができるようになる。

Depending of the contents of modules, the goal is:
To be able to describe what statistical learning is.
To understand supervised/non-supervised learning.
To understand model selection.
To understand regularization.
To understand the basics of tree/neural network/support vector machine.
To understand regression/classification/prediction of statistical learning.
To be able to use Python's basic libraries for machine learning.
Schedule and Contents 基礎A・基礎Bでは、オリエンテーション、に引き続き、それぞれ以下の内容を扱う。

The order of topics is as below.
Basics A:
Supervised learning
Linear method for regression
Linear method for classification
Basis expansion and regularization
Kernel smoothing
Basics B:
Neural network
Support vector machine
Application A:
Introduction to Python
Supervised learning (classificatio and regression)
Non-supervised learning (Dimension reduction and feature extraction, clustering)
Application B:
Introduction to Python
Decision tree
Cross validation
Evaluation Methods and Policy 授業中の質疑応答の発言を評価する。

Activities in the class hours, and homeworks are count.
Course Requirements 前期・後期併せての受講が望ましいが、必須ではない。

Register both the first and second semester classes, if possible.

Study outside of Class (preparation and review) 予習・復習の宿題が出る。

Needs to report to the homework tasks.
Textbooks Textbooks/References Basics A,B
統計的学習の基礎―データマイニング・推論・予測― ISBN 9784320123625
The Elements of Statistical Learning ISBN 978-0387848570
応用A、B:Pythonではじめる機械学習 ―scikit-learnで学ぶ特徴量エンジニアリングと機械学習の基礎 ISBN 978-4873117980、Introduction to Machine Learning With Python: A Guide for Data Scientists ISBN 978-1449369415
References, etc. Will be Introduced during class.