:orphan:

|rss_image|  **2018-10 - 1/1** :ref:`Blog <ap-main-0>` :ref:`article (8) <ap-cat-article-0>` :ref:`articles (3) <ap-cat-articles-0>` :ref:`cours (6) <ap-cat-cours-0>` :ref:`module (7) <ap-cat-module-0>` :ref:`paper (3) <ap-cat-paper-0>`

.. |rss_image| image:: feed-icon-16x16.png
    :target: ../_downloads/rss.xml
    :alt: RSS

----


.. index:: 2018-10


.. _ap-month-2018-10-0:

2018-10 - 1/1
+++++++++++++

.. blogpostagg::
    :title: Fairness - fairlearn - classification
    :date: 2018-10-24
    :keywords: classification,éthique
    :categories: éthique
    :rawfile: 2018/2018-10-24_fair.rst

    Je suis tombé sur ce module
    `fairlearn <https://github.com/Microsoft/fairlearn>`_
    qui s'appuie sur l'article
    `A Reductions Approach to Fair Classification <https://arxiv.org/pdf/1803.02453.pdf>`_.
    L'article définit mathématiquement l'aspect
    éthique qu'il souhaite vérifier dans des modèles
    de machine learning dédiés à la classification.
    L'article commence par définir le triplet
    *(X,A,Y)* où *A* est l'ensemble des attributs protégés,
    *X* l'ensemble des variables, *Y* la chose à prédire.
    On note *h(X)* la prédiction du classifieur binaire.
    L'article définit ensuite la *parité*
    :math:`\pr{h(X) = \hat{y} | A = a} = \pr{h(X) = \hat{y}} \; \forall a, \hat{y} \in \{0, 1\}`,
    puis l'égalité des chances :
    :math:`\pr{h(X) = \hat{y} | A = a, Y = y} = \pr{h(X) = \hat{y} | Y = y}`.
    L'article propose une façon d'apprendre un modèle respectant
    ces contraintes qui s'expriment sous la forme d'un ensemble
    de contraintes linéaires.




.. blogpostagg::
    :title: English content
    :date: 2018-10-13
    :keywords: english content
    :categories: english
    :rawfile: 2018/2018-10-13_english.rst

    Most of the content is written in French.
    Two reaons for that, my teachings are in French,
    most of the content available on the internet
    is already in English. However, there exist some
    English content.
    A good start would be the lectures by
    `Gaël Varoquaux <http://gael-varoquaux.info/>`_ :`.
    :ref:`l-ml-skgael`.
    I wrote some challenges in English one about algorithmic,
    the other one about unsupervized machine learning :
    `Computer Science Challenges <http://www.xavierdupre.fr/app/ensae_projects/helpsphinx/i_challenges.html>`_.
    The main goal of this course is to introduce many
    standard machine learning problems and play with them.
    I suggest doing one competition or study with a known
    datasets (:epkg:`Kaggle`, :epkg:`UCI`).





----

|rss_image|  **2018-10 - 1/1** :ref:`2022-10 (1) <ap-month-2022-10-0>` :ref:`2022-12 (2) <ap-month-2022-12-0>` :ref:`2023-01 (1) <ap-month-2023-01-0>` :ref:`2023-02 (1) <ap-month-2023-02-0>` :ref:`2023-04 (1) <ap-month-2023-04-0>`