Data Science – from theory to practice (CSC70718)

Objectives

The goal of the course is to have a broad introduction on data science and artificial intelligence techniques. The course is split into three parts: 

  • Introduction to Data Science, in which we learn the why data is the value and what are the existing challenges that needs mining of the data.
  • Unsupervised learning, in which we study the concept and some of the related algorithms: hierarchical clustering, kmeans, dbscan, hdbscan, etc.
  • Supervised learning, in which we study the concept and some of the related algorithm: regression (linear and logistic), decision trees, Naïve Bayes, SVM, random forest
  • Text analysis (supervised and unsupervised)  in which we will review the specificities of text analysis

Each course is followed by practical work using R and/or python

Organisation

14 hour coursework, 20 hours practice

Evaluation

Practical session grading

Return to Coursework.