Rémi Flamary

Practical introduction to Machine Learning

Courses

Course overview:

• Data and Machine Learning problems [PDF][PDF_2x2]
  • Data properties and visualization
  • Pre-processing
  • Finding your Machine Learning problem
• Unsupervised learning [PDF][PDF_2x2]
  • Clustering
  • Density estimation and generative modeling
  • Dictionary learning and collaborative filtering
  • Dimensionality reduction and manifold learning
• Supervised learning [PDF][PDF_2x2]
  • Bayesian decision and Nearest neighbors
  • Linear models nonlinear methods for regression and classification
  • Trees, forest and ensemble methods
• Machine learning in practice [PDF][PDF_2x2]
  • Performance measures
  • Models and parameter selection (validation)
  • Interpretation of the methods

Practical sessions

• Practical Session 1 : Unsupervised Learning [PDF] [temper.npz] [digits.npz]
• Practical Session 2 : Regression [PDF] [ECoG.npz]
• Practical Session 3 : Classification [PDF] [pima.npz][digits.npz]

Practical sessions will require a working Python environnement with the libraries Numpy/Scipy and Matplotlib installed. You can get such an environnement for Windows/Linux/MacOSX on Anaconda.

Here is a list of nice references and Python tutorials :

• Tutorial Numpy
• Doc Numpy
• Doc Scipy
• Doc ScMatplotlib/pylab

Bibliography

• Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning (Vol. 1, No. 10). New York: Springer series in statistics. [PDF]
• Bishop, C. M. (2006). Pattern recognition. Machine learning, 128(9).
• Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press. [URL]
• Ng Andrew, Coursera [URL]