CCO - 740 - Pattern Recognition

Total of Credits: 8
Hours for Theoretical Classes: 60
Hours for Exercises or Seminars: 60

Objective

  • To provide the students with the mathematical tools for the development of pattern recognition and machine learning systems. At the end of the course, the student should be able to:
  • design and code linear or non-linear supervised classifiers from a broad set of paradigms (Bayes decision theory, Methods based on artificial neurons, Support Vector Machines, Logistic regression, among other non-parametric approaches);
  • design and code unsupervised classifiers to find clusters in multivariate data (hierarquical clustering, k-means, Gaussian mixture models and the Expectation-Maximization algorithm);
  • design and code feature extraction methods for dimensionality reduction (Principal Component Analysis, Linear Discriminant Analysis, Kernel PCA);
  • assess the supervised classification performance using quantitative metrics (confusion matrix, accuracy, Kappa coefficient)

Catalog Description

  • Supervised classification: Perceptron, Adaline (Widrow-Hoff), Logistic regression, Bayes Decision Theory, Bayesian classifier under Gaussian hypothesis, minimum distance classifier, K-nearest neighbors, support vector machines.
  • Unsupervised classification: Hierarquical clustering, the k-means algorithm, Gaussian mixture models and the Expectation-Maximization algorithm.
  • Feature extraction
  • Linear methods for dimensionality reduction: Principal component analysis (PCA), Linear discriminant analysis (LDA), Non-negative matrix factorization (NMF)
  • Non-linear Kernel based methods: Kernel PCA
  • Performance evaluation metrics: confusion matrix, accuracy, precision and recall, F1-score, Cohen's Kappa coefficient. Error/Accuracy estimation methods: holdout, resubstitution, k-fold cross validation and leave-one-out cross validation.
  • Advanced topics and new trends: Manifold learning, neural networks, backpropagation, deep learning, metric learning, etc.

Bibliography

  1. Richard O. Duda, Peter E. Hart, David G. Stork, Pattern Classification, 2nd Edition, Wiley-Interscience, 2000 (disponível na BCO).
  2. Andrew R. Webb, Keith D. Copsey, Statistical Pattern Recognition, 3rd Edition, Wiley, 2011 (disponível na BCO).
  3. Sergios Theodoridis, Konstantinos Koutroumbas, Pattern Recognition, 4th Edition, Academic Press, 2008 (disponível na BCO).
  4. Keinosuke Fukunaga, Introduction to Statistical Pattern Recognition, 2nd Edition, Academic Press, 2013 (disponível na BCO).
  5. Geoff Dougherty, Pattern Recognition and Classification: An Introduction, Springer, 2013.
  6. Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition, Springer, 2016.
  7. Kevin P. Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012.
  8. Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2011.
  9. Jürgen Schürmann, Pattern Classification: A Unified View of Statistical and Neural Approaches, 1st Edition, Wiley-Interscience, 1996.