Knowledge

The student

can understand the basic data structures and algorithms for machine learning.
knows the mathematical concepts underlying the design and analysis of machine learning techniques appropriate for a given data science problem
has insights into the strengths and weaknesses of Dimensionality Reduction Algorithms: variance thresholds, correlation thresholds, principal component analysis (PCA), linear discriminant analysis (LDA)
can explain the basic natural language processing concepts and techniques for text analytics
knows the text analytics methods and tools (such as text classification, semantic textual similarity, word sense disambiguation and neural language models) for various data science domains

Skills

The student

can select appropriate machine learning methods (such as linear models, classification models, text classification, semantic textual similarity, word sense disambiguation and neural language models) and tools for a given data science problem
can analyze mathematically the performance of machine learning methods and techniques
can apply techniques from the course to new data science problems in terms of selection of appropriate machine learning methods, techniques and tools
can use python or similar to implement machine learning methods and techniques
can discuss concepts and applications of machine learning (including text)

General competence

The student

can differentiate the suitability and efficiency of programs in terms of the machine learning methods and techniques (incl. text analytics) employed
can apply the knowledge of and skills in machine learning in various data science domains
can critically reflect on the tradeoffs in the design and implementation of machine learning methods and techniques.

Subject description PGR210

Machine Learning and Natural Language Processing