Google translated http://scikit-learn.org/0.18/tutorial/statistical_inference/index.html. scikit-learn 0.18 Tutorial Table of Contents Previous tutorial
Machine learning (https://en.wikipedia.org/wiki/Machine_learning) is an increasingly important technology due to the rapidly growing size of experimental science datasets. We are tackling a variety of problems, from building predictive functions that link different observations to classifying observations or learning the structure of unlabeled datasets. This tutorial will show you how to use machine learning techniques for the purpose of Statistical Inference (https://en.wikipedia.org/wiki/Statistical_inference) as a result of statistical learning with data as clues. scikit-learn is a classic machine learning algorithm for scientific Python packages (NumPy, SciPy, [matplotlib]. ](Http://matplotlib.org/)) is a tightly organized Python module integrated into the world.
--Curse of dimensionality and nearest neighbor --Linear model: from regression to sparseness --Support Vector Machine (SVM)
--Score, cross-validated score --Cross-validation generator --Grid search and cross-validated estimator
--Clustering: Group observations together --Decomposition: From signal to component and loading
--Pipeline processing --Face recognition by eigenface --Open problem: Stock market structure
--Project mailing list --Q & A community with machine learning practitioners
2010 --2016, scikit-learn developers (BSD license).
Recommended Posts