Selected topics

• data split (train, test, validation)
• mini-batch
• cross-validation
• bias-variance trade-off
• gradient
• “Points clefs” and interesting references from Azencott’s textbook

References

(can all be found online)

• Books (English)
  • The elements of statistical learning - Hastie et al.
  • Deep learning - Goodfellow et al.
  • Machine learning: a probabilistic perspective - Murphy
  • Pattern recognition and machine learning - Bishop
  • Neural networks and deep learning - Nielsen
  • Dive into Deep Learning - Zhang et al.
  • Statistical learning with sparsity: the lasso and generalizations - Hastie et al. s - Bayesian reasoning and machine learning - Barber
  • Deep learning: a practitioner’s approach - Gibson and Patterson
  • Neural networks and deep learning - Aggarwal
  • An introduction to statistical learning with applications in R - James et al.
  • Big data et machine learning manuel du data scientist - Lemberger et al.
• Books (French)
  • Introduction au Machine Learning - Azencott
  • Le Machine learning avec R - Modélisation mathématique rigoureuse - Burger
  • Data science fondamentaux et études de cas Machine learning avec Python et R - Biernat and Lutz
  • Data Science par la pratique - Grus
• Online ressources
  • interactive machine learning articles on Distill
  • explore neural networks with http://playground.tensorflow.org
  • blog on selected machine learning topics
  • learning methods building on kernels
  • teaching page of Prof. Chloé-Agathe Azencott (book, slides and notebooks)
  • Convolutional Neural Networks for Visual Recognition - Stanford CS class