The School of Mathematics Whittaker Colloquium will be given by Professor Andrew Blake (Founding Director of the Alan Turing Institute) at 4PM on Friday, 27th May in Lecture Room A of the James Clerk Maxwell Building on the King's Buildings campus.
"Machines that see powered by probability"
Abstract: The newly established Alan Turing Institute researches data science, at the intersection of mathematics, statistics, computer science, social science and software engineering. One of the core topics at that intersection is probabilistic processing. For example, machines that see cannot, it turns out, be programmed directly, but must learn from data, and that involves computing with probabilities. Such machines bring benefits to safety, consumer experiences, and healthcare, and their operation is based on mathematical ideas.These ideas fit into a philosophy of vision as inference: exploring hypotheses for the contents of a scene that explain an image as fully as possible. More recently this explanatory approach has partly given way to powerful, direct estimation methods, whose operating parameters are learned from large data sets. Perhaps the most capable vision systems will come ultimately from some kind of fusion of the two approaches.