Performing supervised learning from the data synthesized by using Genera...
Deep Learning techniques have achieved remarkable results in many domain...
We estimate the proper channel (width) scaling of Convolution Neural Net...
This paper proposes backward reduction, an algorithm that explores the
c...
We propose a block-diagonal approximation of the positive-curvature Hess...
Scale of data and scale of computation infrastructures together enable t...
Deep learning owes its success to three key factors: scale of data, enha...