.. _l-td2A-biblio:
=============
Bibliographie
=============
.. contents::
:local:
Livres sur le machine learning
==============================
* `The Elements of Statistical Learning `_, Trevor Hastie, Robert Tibshirani, Jerome Friedman
* `Python for Data Analysis `_, Wes McKinney
* `Building Machine Learning Systems with Python
`_,
Willi Richert, Luis Pedro Coelho
* `Learning scikit-learn: Machine Learning in Python
`_,
Raúl Garreta, Guillermo Moncecchi
* `Modeling Creativity: Case Studies in Python `_, Tom De Smedt
* `Deep Learning `_,
Yoshua Bengio, Ian Goodfellow and Aaron Courville
* `Artificial Intelligence: A Modern Approach `_,
Stuart Russell, Peter Norvig
* `Speech and Language Processing `_, Daniel Jurafsky and James H. Martin,
voir aussi `Draft chapters in progress `_
* `The Hundred Page Machine Learning `_, Andriy Burkov
(sur github : ` `_)
* `Critical Mass: How One Thing Leads to Another
`_,
Philip Ball
Livres sur les algorithmes
==========================
* `Introduction to Algorithms `_,
Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest and Clifford Stein
* `The Algorithm Design Manual `_, Steven S. Skiena
* `Competitive Programming `_, Steven Halim
Livres sur la programmation
===========================
* `High Performance Python `_, Micha Gorelick, Ian Ozsvald.
Le livre est très bien conçu et les exemples sont très clairs. Si vous souhaitez accélérer un programme Python
en utilisant le multithreading, `OpenMP `_,
`Numba `_, `Cython `_
`PyPy `_, ou `CPython `_,
je recommande d'y jeter un coup d'oeil d'abord.
Liens sur la programmation
==========================
* `Python Scientific Lecture Notes `_
* `Introduction to matplotlib `_
* `Introduction to Data Processing with Python `_
* Quelques idées de livres : `Python for Data Scientists `_
* `Ultimate guide for Data Exploration in Python using NumPy, Matplotlib and Pandas `_
* `Don't use Hadoop - your data isn't that big `_
* `Prédire les épidémies avec Wikipedia `_, Le Monde
* `FastML `_ (blog sur le machine learning)
* `Mathematical optimization: finding minima of functions `_
* `you can take the derivative of a regular expression?! `_ *(2016/06)*
* `How to trick a neural network into thinking a panda is a vulture `_ *(2016/06)*
* `Matrix Factorization: A Simple Tutorial and Implementation in Python `_ *(2016/06)*
* `Top-down learning path: Machine Learning for Software Engineers `_
Tutoriels
=========
* `PyData Seattle 2015 Scikit-learn Tutorial `_ *(2015/12)*
* `Pythonic Perambulations `_ *(2015/12)*
* `Python Scripts posted on Kaggle `_ *(2016/02)*
* `Pandas cookbook `_ *(2016/06)*
* `Machine Learning & Deep Learning Tutorials `_ *(2016/06)* :
lien vers une liste assez longue de tutoriels, on y trouve aussi des *cheat sheets* comme
`Probability Cheatsheet `_
MOOC
====
* `Machine Learning par Andrew Y. Ng `_
(les chapitres X et XI de la semaine 6 aborde la construction d'un système de machine learning).
* `Coursera Machine Learning `_
* `Coursera Machine Algorithm `_
* `CSE373 - Analysis of Algorithms - 2007 SBU `_
* `CS109 Data Science (Harvard) `_ (la liste des vidéos disponibles est en bas)
Autres cours, notebooks
=======================
* `Arthur Charpentier, lectures `_ (français)
* `CS109 Data Science (Harvard) `_ -
`TD `_ -
`Talks `_
* `Notes and assignments for Stanford CS class CS231n `_
`Convolutional Neural Networks for Visual Recognition `_
* `Advanced Statistical Computing, Chris Fonnesbeck (Vanderbilt University) `_
* `CS 188: Artificial Intelligence (Berkeley) `_
* `IAPR: Teaching materials for machine learning `_
* machine learning et musique `Audio Content Analysis, teachings `_
* `ogrisel's notebook `_ (2016/04)
* `L'apprentissage profond `_, Yann LeCun au Collège de France *(2016/06)*
* `MA 2823 Foundations of Machine Learning (Fall 2016) `_ *(2016/10)*
Articles d'auteurs très connus
==============================
* `Latent Dirichlet Allocation `_, David M. Blei, Andrew Y. Ng, Michael I. Jordan
* `Analysis of a Random Forests Model `_, Gerard Biau
* `Adaptivity of Averaged Stochastic Gradient Descent to Local Strong Convexity for Logistic Regression `_, Francis Bach
* `Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising `_, Léon Bottou, Jonas Peter et Al.
* `Tutorial on Practical Prediction Theory for Classification `_, John Langford
* `Sparse Online Learning via Truncated Gradient `_, John Langford, Lihong Li, Tong Zhang
* `Low-dimensional Embeddings for Interpretable Anchor-based Topic Inference `_, Moontae Lee, David Mimno
* `ABC model choice via random forests `_, Pierre Pudlo, Jean-Michel Marin, Arnaud Estoup, Jean-Marie Cornuet, Mathieu Gautier, Christian P. Robert
* `Mondrian Forests: Efficient Online Random Forests `_, Balaji Lakshminarayanan, Daniel M. Roy, Yee Whye Teh
* `Stochastic Gradient Tricks `_
* `SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases `_, Simon Lacoste-Julien, Konstantina Palla, Alex Davies, Gjergji Kasneci, Thore Graepel, Zoubin Ghahramani
* `Learning from Partial Labels `_, Timothee Cour, Benjamin Sapp, Ben Taskar
* `Word Alignment via Quadratic Assignment `_, Simon Lacoste-Julien, Ben Taskar, Dan Klein, Michael I. Jordan
* `Contextual Bandit Learning with Predictable Rewards `_, Alekh Agarwal, Miroslav Dudík, Satyen Kale, John Langford, Robert E. Schapire
* `Learning from Logged Implicit Exploration Data `_, Alex Strehl, John Langford, Lihong LiSham, M. Kakade
* `The Metropolis-Hastings algorithm `_, Christian P. Robert
* `From RankNet to LambdaRank to LambdaMART: An Overview `_, Christopher J.C. Burges
Compétition de code
===================
* `Google Hash Code `_, a lieu chaque année en deux tours, le second tour a lieu chez Google à Paris.
* `Google Code Jam `_
* `TopCoder `_
* `UVa Online Judge `_
* `Le problème des huit reines `_
* `Projet Euler `_
Compétition de machine learning
===============================
* `datascience.net `_
* `Kaggle `_
* `ImageNet `_
* `SQuAD `_
Sources d'articles scientifiques
================================
* `ShortScience.org `_
* `Journal of Machine Learning Research `_
Pour finir, `Choosing the right estimator `_ :
.. image:: http://scikit-learn.org/stable/_static/ml_map.png
:width: 500
Librairies
==========
* `Simple/limited/incomplete benchmark for scalability, speed and accuracy of machine learning libraries for classification `_
* `Python extensions to do machine learning `_
* `Related Projects (of machine learning) `_ (2016/03)
* `Awesome Machine Learning `_
* Chaque paragraphe recense des librairies connues sur le sujet.
Vidéos
======
* `Beyond Bag of Words A Practitioner's Guide to Advanced NLP `_
* `Building Continuous Learning Systems `_