Education & Resources

In the past decade, deep learning methods have achieved unprecedented performance on a broad range of problems in various fields from computer vision to speech recognition. So far research has mainly focused on developing deep learning methods for Euclidean-structured data.

In this webinar, we'll introduce FemtoPixel: A framework for lensless imaging with compressive ultrafast sensing. The FemtoPixel framework provides single-pixel imaging capabilities that are up to 50X faster compared to traditional single-pixel camera techniques. 

This webinar will address the problem of identifying the structure of an undirected graph from the observation of signals defined on its nodes. Fundamentally, the unknown graph encodes direct relationships between signal elements, which we aim to recover from observable indirect relationships generated by a diffusion process on the graph. 

Upcoming webinar, 29 January 2019 by Dr. Victor Elvira. In many problems of signal processing, the interest is in estimating unknown static variables given a set of observations. The hidden parameters and the available data are usually related through a specific model.