33 citations · 48 across the 4 of their papers we have counts for
5 papers
Low precision logarithmic number systems: Beyond base-2
Syed Asad Alam, James Garland, David Gregg
Logarithmic number systems (LNS) are used to represent real numbers in many applications using a constant base raised to a fixed-point exponent making its distribution exponential.…
Feature Representation in Deep Metric Embeddings
Ryan Furlong, Vincent O'Brien, James Garland +2
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 toget…
HOBFLOPS CNNs: Hardware Optimized Bitslice-Parallel Floating-Point Operations for Convolutional Neural Networks
James Garland, David Gregg
Convolutional neural networks (CNNs) are typically trained using 16- or 32-bit floating-point (FP) and researchers show that low-precision floating-point (FP) can be highly effecti…
Low Complexity Multiply-Accumulate Units for Convolutional Neural Networks with Weight-Sharing
James Garland, David Gregg
Convolutional neural networks (CNNs) are one of the most successful machine learning techniques for image, voice and video processing. CNNs require large amounts of processing capa…
Low Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks
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. CNNs require large amounts of pro…