Information decomposition

Juergen Jost

MPI for Mathematics in the Sciences, Leipzig
Monday, September 17, 2018 at 12:00pm
560 Evans

In many situations, two or more sources have some information about a target. For instance, sensory input and context information can jointly determine the firing pattern of a neuron. Since the information from the two sources is typically not identical, one wishes to decompose it in those parts that are unique to each source, what is shared between them and what is complementary, that is, becomes useful only when the two sources are combined. This has been an active research topic in recent years, to which our group, including Johannes Rauh, Nils Bertschinger, Eckehard Olbrich, Nihat Ay, Pradeep Banerjee, has contributed, with some surprising findings. Possible applications to neuroscience will also be discussed.