Machine Learning (Aprendizado de Máquina)

Pós-graduação em Ciência da Computação

Instituto de Computação, Universidade Federal Fluminense.

Campus Praia Vermelha, Niterói.

As the 2016.1 semester is over I am updating this page in preparation for 2016.2. Bear in mind that the content is being modified.

Syllabus (Ementa)

The course provides an introduction to the foundations of machine learning. We will discuss the following topics:

  • Basic machine learning concepts;
  • classes of problems;
  • data representation and attributes;
  • supervised, unsupervised semi-supervised and reinforcement;
  • regression algorithms;
  • classification algorithms;
  • clustering algorithms;
  • generalization, bias/variance dilemma, overfitting;
  • performance assessment.

Class organization

The course is supported by a set of Jupyter/IPython notebooks.

You can also retrieve the notebooks from GitHub and run them locally for a better experience by cloning the git repository.

Similarly, you can use binder to run the notebooks online. In this case, bear in mind that all the changes you make can be lost.

Students must enroll on the class online LMS at Whenever possible use piazza for all communications. If not, include TIC10021 in the subject of your emails.

Please give yourself a profile picture – this will be really useful for all of us to learn each other’s names.


Reading list

This reading list contains papers that we have commented or discussed in class but that are not necessarily essential to the course. Feel free to contribute to the list via the Mendeley group.


Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov (2014) Dropout : A Simple Way to Prevent Neural Networks from Overfitting, Journal of Machine Learning Research (JMLR) 15, p. 1929-1958, doi:10.1214/12-AOS1000

Jürgen Schmidhuber (2014) Deep Learning in Neural Networks: An Overview, arXiv preprint arXiv:1404.7828 abs/1404.7, p. 1-60, url, doi:10.1016/j.neunet.2014.09.003


Geoffrey E Hinton (2011) Machine learning for neuroscience, Neural Systems & Circuits 1(1), p. 12, BioMed Central, url, doi:10.1186/2042-1001-1-12


Xavier Glorot, Yoshua Bengio (2010) Understanding the difficulty of training deep feedforward neural networks, Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS) 9, p. 249-256, pdf, doi:


Rui Xu, Donald Wunsch (2005) Survey of clustering algorithms., IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council 16(3), p. 645-78, pubmed, doi:10.1109/TNN.2005.845141


Nizar Grira, Michel Crucianu, Nozha Boujemaa (2004) Unsupervised and semi-supervised clustering: a brief survey, A Review of Machine Learning …, p. 1-12, pdf


M. Olazaran (1996) A Sociological Study of the Official History of the Perceptrons Controversy, Social Studies of Science 26(3), p. 611-659, doi:10.1177/030631296026003005


Shigeru Watanabe, Junko Sakamoto, Masumi Wakita (1995) Pigeons' discrimination of paintings by Monet and Picasso, Journal of the Experimental Analysis of Behavior 63(2), p. 1334394, url, doi:10.1901/jeab.1995.63-165

Questions and doubts

Students can book a meeting with the professor using the form bellow.