2020年9月19日
An Epistemic Approach to the Formal Specification of Statistical Machine Learning
Software and Systems Modeling
- 巻
- 20
- 号
- 2
- 開始ページ
- 293
- 終了ページ
- 310
- 記述言語
- 英語
- 掲載種別
- 研究論文(学術雑誌)
- DOI
- 10.1007/s10270-020-00825-2
- 出版者・発行元
- Springer
We propose an epistemic approach to formalizing statistical properties of machine learning. Specifically, we introduce a formal model for supervised learning based on a Kripke model where each possible world corresponds to a possible dataset and modal operators are interpreted as transformation and testing on datasets. Then we formalize various notions of the classification performance, robustness, and fairness of statistical classifiers by using our extension of statistical epistemic logic. In this formalization, we show relationships among properties of classifiers, and relevance between classification performance and robustness. As far as we know, this is the first work that uses epistemic models and logical formulas to express statistical properties of machine learning, and would be a starting point to develop theories of formal specification of machine learning.
- リンク情報
-
- DOI
- https://doi.org/10.1007/s10270-020-00825-2 本文へのリンクあり
- 共同研究・競争的資金等の研究課題
- 機械学習システムの品質評価指標・測定テストベッドの研究開発
- 共同研究・競争的資金等の研究課題
- 蓮尾メタ数理システムデザイン
- URL
- https://rdcu.be/b7ssR 本文へのリンクあり
- ID情報
-
- DOI : 10.1007/s10270-020-00825-2