Credit points: 3.0
Data science waves have brought change in multiple disciplines from scienceand technology through business and society, hitting with full force in the lastcouple of years with the re-introduction of Deep Learning paradigm. With theincreasing amount of data being created in the world through the developmentof the web, social networks and internet commerce - the need for automatedmethods for data analysis is growing rapidly.In this course we will deep dive to the cutting-edge research in NLP andrelated disciplines and explore the state of the art methods in those fields.We will explore practical algorithms that have been used to solve keyproblems in data mining and can be applied successfully to even the largestdatasets.
During the course we will cover the theory and practice of decision trees,SVM, graphical models, neural network models (including: word vectorrepresentations, window-based neural networks, recurrent neural networks,long-short-term-memory models, recursive neural networks, and convolutionalneural networks) and explore other data mining applications such asClustering, Massive Graphs Mining, and Recommender Systems.The goal of the course to make you the best data-scientist and practitionerwherever you go next. For undergraduate student, the course will be based on a final project done on a real problem from theindustry in a competition mode. For graduate students, we will conduct an oral exam.
The course is aimed at graduate students with some basic knowledge ofmachine learning (and possibly but not necessarily of deep learning) and wishto learn more about this rapidly growing field of research.