no code implementations • 12 Feb 2021 • Syed Asad Alam, James Garland, David Gregg
Second, we show that low-precision LNS addition and subtraction can be implemented efficiently in logic rather than commonly used ROM lookup tables, the complexity of which can be reduced by an appropriate choice of base.
Numerical Analysis Numerical Analysis Signal Processing 65G50 C.m; G.0
no code implementations • 5 Feb 2021 • Ryan Furlong, Vincent O'Brien, James Garland, Daniel Palacios-Alonso, Francisco Dominguez-Mateos
In deep metric learning (DML), high-level input data are represented in a lower-level representation (embedding) space, such that samples from the same class are mapped close together, while samples from disparate classes are mapped further apart.
no code implementations • 11 Jul 2020 • James Garland, David Gregg
HOBFLOPS allows researchers to prototype different levels of custom FP precision in the arithmetic of software CNN accelerators.
no code implementations • 30 Aug 2016 • James Garland, David Gregg
Convolutional Neural Networks (CNNs) are one of the most successful deep machine learning technologies for processing image, voice and video data.