“Abstract—Large-scale distributed deep learning training has enabled developments of more complex deep neural network models to learn from larger datasets for sophisticated tasks. In particular, ...

The most widely used technique for finding the largest or smallest values of a math function turns out to be a fundamentally difficult computational problem. Many aspects of modern applied research ...

SIAM Journal on Numerical Analysis, Vol. 15, No. 6 (Dec., 1978), pp. 1247-1257 (11 pages) This paper studies the convergence of a conjugate gradient algorithm proposed in a recent paper by Shanno. It ...

TPU researchers have developed a new gradient microarchitecture for diamond coatings. It consists of smoothly alternating ...