Sparse decision making: how to classify using very few sensors


April 14, 2014 - 4:00pm
NW 343
About the Speaker
Bingni Brunton (University of Washington)

I will speak about our recent work developing an algorithm that harnesses enhanced sparsity, the orders-of-magnitude reduction in number of measurements required for signal classification over reconstruction. This sparse sensors algorithm provides one approach to the question, given a fixed budget of sensors, where should they be placed to optimally inform decision making? I will show an example were this reverse engineering approach contributes to our understanding of how biological organisms acquire information about a complex environment. Further, the same approach has applications to engineering devices to interact with neural systems.