For more and more companies, InDesign is the defacto standard for brochure, magazine & poster design. In this course you will learn how to use InDesign to stitch your publication together, arrange ...

Abstract: We present a robust FFT-based approach to scale-invariant image registration. Our method relies on FFT-based correlation twice: once in the log-polar Fourier domain to estimate the scaling ...

Training very deep neural networks requires a lot of memory. Using the tools in this package, developed jointly by Tim Salimans and Yaroslav Bulatov, you can trade off some of this memory usage with ...

SVGD is a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization. SVGD iteratively transports a set of particles to match with the target ...

Abstract: Deep neural networks often suffer from poor performance or even training failure due to the ill-conditioned problem, the vanishing/exploding gradient problem, and the saddle point problem.