University of Edinburgh

This course covers some of the linguistic and algorithmic foundations of natural language processing (NLP). It builds on algorithmic and data science concepts developed in previous courses, applying these to NLP problems. It also equips students for more advanced NLP courses. The course is strongly empirical, using corpus data to illustrate both core linguistic concepts and algorithms, including language modeling, part of speech tagging, syntactic processing, the syntax-semantics interface, and aspects of semantic and pragmatic processing. The theoretical study of linguistic concepts and the application of algorithms to corpora in the empirical analysis of those concepts are interleaved throughout the course.

This is an introductory astronomy course that should be accessible to any student. We assume a basic level of numeracy, but no mathematics more complicated than simple algebra and simple trigonometry is used. The course covers a wide range of topics, from understanding our sun and solar system through to cosmology and the Big Bang.

The course examines some of the important recent developments in economics, focusing mainly, but not exclusively, on key contributions since 1950, especially those whose authors were awarded the Nobel Prize in Economic Science. Through an examination of the original as well as more modern academic literature, it will look at analytical concepts and techniques that were once novel but are now widely accepted. The course also touches on the historical context in which economics evolved.

This course teaches about bio-inspired algorithms for optimization and search problems. The algorithms are based on simulated evolution (including Genetic algorithms and Genetic programming), particle swarm optimization, ant colony optimization as well as systems made of membranes or biochemical reactions among molecules. These techniques are useful for searching very large spaces. For example, they can be used to search large parameter spaces in engineering design and spaces of possible schedules in scheduling. However, they can also be used to search for rules and rule sets, for data mining, for good feed-forward, or recurrent neural nets and so on. The idea of evolving, rather than designing, algorithms and controllers is especially appealing in AI. In a similar way it is tempting to use the intrinsic dynamics of real systems consisting e.g. of quadrillions of molecules to perform computations for us. The course includes technical discussions about the applicability and a number of practical applications of the algorithms.