← Search

Pradeep Dubey

2 accepted papers

2018

Mixed Precision Training of Convolutional Neural Networks using Integer Operations

ICLR 2018poster

The state-of-the-art (SOTA) for mixed precision training is dominated by variants of low precision floating point operations, and in particular, FP16 accumulating into FP32 Micikevicius et al. (2017). On the other hand, while a lot of research has also happened in the domain of low and mixed-precisi…

Cited by 226SourcePDFScholar
2017

Faster CNNs with Direct Sparse Convolutions and Guided Pruning

ICLR 2017poster

Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and undesirable. Consequently, various methods have been develo…

Cited by 307SourcecodeScholar