The course provides an introduction to the foundations of machine learning. We will discuss the following topics:
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 piazza.com. 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.
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.
(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
(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:10.1.1.207.2059
(2004) Unsupervised and semi-supervised clustering: a brief survey, A Review of Machine Learning …, p. 1-12, pdf
(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
Students can book a meeting with the professor using the form bellow.