コンテンツに飛ぶ | ナビゲーションに飛ぶ

  • 日本語
  • English
 
現在位置: ホーム ja シラバス(2020年度) 工学研究科 デザイン学分野 統計的学習理論

統計的学習理論

JA | EN

科目ナンバリング
  • G-ENG76 63178 LE10
開講年度・開講期 2020・前期
単位数 2 単位
授業形態 講義
配当学年 博士
対象学生 大学院生
使用言語 英語
曜時限 月1
教員
  • 鹿島 久嗣(情報学研究科 教授)
  • 山田 誠(情報学研究科 准教授)
授業の概要・目的 This course will cover in a broad sense the fundamental theoretical aspects and applicative possibilities of statistical machine learning, which is now a fundamental block of statistical data analysis and data mining. This course will focus on the supervised and unsupervised learning problems, including theoretical foundations such as a survey of probably approximately correct learning as well as their Bayesian perspectives and other learning theory frameworks. Several probabilistic models and prediction algorithms, such as the logistic regression, perceptron, and support vector machine will be introduced.
Advanced topic such as online learning, transfer learning, and sparse modeling will be also introduced.
到達目標 Understanding basic concepts, problems, and techniques of statistical learning and some of the recent topics
授業計画と内容 1. Statistical Learning Theory
1-1. Introduction to classification & regression: historical perspective, separating hyperplanes and major algorithms
1-2. Probabilistic framework of classification and statistical learning theory: Learning Bounds, Vapnik-Chervonenkis theory

2. Supervised Learning
2-1 Models for Classification: Logistic Regression, Perceptron, Support Vector Machines
2-2 Regularization: Sparse Models (L1 regularization), Bayesian Interpretations
2-3 Model Selection: Performance Measures, Cross-Validation, and Other Information Criterion


3. Advanced topics
3-1 Online learning
3-2 Semi-supervised, Active, and Transfer Learning
成績評価の方法・観点 Reports and final exam.
履修要件 特になし
授業外学習(予習・復習)等 Basic knowledge about probability and statistics
参考書等
  • Hastie, Friedman, Tibshirani 『The Elements of Statistical Learning』 (Springer) Shai Shalev-Shwartz and Shai Ben-David 『Understanding Machine Learning: From Theory to Algorithms』 (Cambridge University Press)