• 講義要項やWebシラバスの記載内容は、登録された受講生の人数や理解度に応じて、授業開始後に変更となる可能性があります。

main start


開講年度 2019年度 開講箇所 グローバルエデュケーションセンター
Machine Learning for Advanced Integrated Intelligence α


担当教員 朝日 透/谷口 卓也/丸山 祐丞
学期曜日時限 集中講義(春学期)  土その他
科目区分 ユニバーシティ・スタディーズ科目 配当年次 1年以上 単位数 1
使用教室 ホール キャンパス 日本橋
科目キー 9S91010031 科目クラスコード 01
授業で使用する言語 英語
  コース・コード INFI611S
大分野名称 情報学
中分野名称 知的システム
小分野名称 一般
レベル 修士レベル 授業形態 演習/ゼミ


最終更新日時:2019/04/01 10:35:01

副題 Super-FundamentaLclass of Machine Learning for Airtificial Intelligence

Thisclass aims to provide the basic knowledge needed to acquire science of machinelearning, which represents the main vehicle of the artificial intelligencefield. Students will learn basic concept, theorem and technique of machinelearning in the first half of lecture. In the last half of lecture, studentswill learn some basic analysis models such as decision tree, and neural network.The language of the instruction is English.

授業の到達目標 This class aims to provide the basic knowledge needed to acquire science of machine learning, which represents the main vehicle of the artificial intelligence field.
事前・事後学習の内容 Read pre-work items in advance before each lecture when they are indicated by faculties. Reports about lessons learned at the lecture are submitted to the faculties at the classroom or through Course-N@vi system.

1st April 6/13:00-14:30, Introduction to Machine Learning,Takuya Taniguchi

2nd April 6/14:45-16:15, Cost Function,Gradient Descent, Takuya Taniguchi

3rd April 13/13:00-14:30, Overfitting, TakuyaTaniguchi

4th  April 13/14:45-16:15, Cross-validation andBias-variance Decomposition, Takuya Taniguchi

5th April20/13:00-14:30, Classification and Logistic Regression, YusukeMaruyama, Takuya Taniguchi

6th April20/14:45-16:15, Decision Tree and Random forest, Yusuke Maruyama,Takuya Taniguchi

7th April27/13:00-14:30, Neural Network, Yusuke Maruyama, Takuya Taniguchi

8th April27/14:45-16:15, Exam, Takuya Taniguchi

割合 評価基準
試験: 40% In the final day, the students must take the examination to get the credit.
レポート: 30% The students must submit the report for issues, which are indicated by faculty members, to them.
平常点評価: 20% The on-site contribution to the class is evaluated.
その他: 10% The participation in symposia and workshops, which are announced by faculties, are strongly recommended.


Copyright © Media Network Center,Waseda University 2006-2019.All rights reserved.