Serwisy internetowe Uniwersytetu Warszawskiego Nie jesteś zalogowany | zaloguj się
katalog przedmiotów - pomoc

Responsible Machine Learning

Informacje ogólne

Kod przedmiotu: 2400-SZD-QPE-RML Kod Erasmus / ISCED: (brak danych) / (brak danych)
Nazwa przedmiotu: Responsible Machine Learning
Jednostka: Wydział Nauk Ekonomicznych
Grupy: Przedmioty WNE dla programu QPE w Międzydziedzinowej Szkole Doktorskiej (ZIP)
Punkty ECTS i inne: (brak)
Język prowadzenia: angielski
Rodzaj przedmiotu:

nieobowiązkowe

Skrócony opis:

The aim of the classes is to familiarize participants with the issues of responsible machine learning. This will allow for the correct design of the machine learning experiment. In particular, we will discuss the basic techniques of explainable machine learning and the measures used in the assessment of fairness. In addition to seminar-type meetings, examples using R and Python will be presented.

Pełny opis:

During this class we will discuss:

• Basics of machine learning.

• Global methods of explaining the model, such as permutation importance of variables, Partial dependence profiles.

• Methods of local model explanation, such as Shapley values, LIME, Break-Down, Ceteris paribus.

• Methods of fairness analysis of a model.

• We will discuss examples of literary failures related to ML models.

Apart from the seminar formula, students will prepare a short essay on cases of using responsible ML.

This essay and its presentation will be the basis for the credit.

Bibliography: Fairness and machine learning

Limitations and Opportunities

Solon Barocas, Moritz Hardt, Arvind Narayanan

https://fairmlbook.org/

Explanatory Model Analysis

Explore, Explain, and Examine Predictive Models. With examples in R and Python.

Przemyslaw Biecek and Tomasz Burzykowski

https://pbiecek.github.io/ema/

A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing

Navdeep Gill, Patrick Hall, Kim Montgomery, Nicholas Schmidt

https://www.mdpi.com/2078-2489/11/3/137

Literatura:

Fairness and machine learning

Limitations and Opportunities

Solon Barocas, Moritz Hardt, Arvind Narayanan

https://fairmlbook.org/

Explanatory Model Analysis

Explore, Explain, and Examine Predictive Models. With examples in R and Python.

Przemyslaw Biecek and Tomasz Burzykowski

https://pbiecek.github.io/ema/

A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing

Navdeep Gill, Patrick Hall, Kim Montgomery, Nicholas Schmidt

https://www.mdpi.com/2078-2489/11/3/137

Efekty uczenia się:

By the end of the course, the student will be familiar:

- with basic machine learning techniques,

- with the area of eXplainable Artificial Intelligence,

- with the area of fairness and transparency of Machine Learning.

Metody i kryteria oceniania:

By project. The course grade will be based on the preparation of a use case for Responsible ML, which will be described in the form of a short essay in an open ebook. See for example https://pbiecek.github.io/xai_stories/.

The readability of the description, relevance for ML modelling and innovation related to new RML applications will be assessed.

Zajęcia w cyklu "Semestr letni 2020/21" (zakończony)

Okres: 2021-02-22 - 2021-06-13
Wybrany podział planu:


powiększ
zobacz plan zajęć
Typ zajęć: Warsztaty, 30 godzin więcej informacji
Koordynatorzy: Przemysław Biecek
Prowadzący grup: Przemysław Biecek
Lista studentów: (nie masz dostępu)
Zaliczenie: Przedmiot - Zaliczenie
Warsztaty - Zaliczenie
Opisy przedmiotów w USOS i USOSweb są chronione prawem autorskim.
Właścicielem praw autorskich jest Uniwersytet Warszawski.