no code implementations • 30 Sep 2023 • Cameron Shinn, Collin McCarthy, Saurav Muralidharan, Muhammad Osama, John D. Owens
We achieve this through a novel analytical model for predicting sparse network performance, and validate the predicted speedup using several real-world computer vision architectures pruned across a range of sparsity patterns and degrees.
no code implementations • 9 Jun 2023 • Harvey Dam, Vinu Joseph, Aditya Bhaskara, Ganesh Gopalakrishnan, Saurav Muralidharan, Michael Garland
E. g., it has been shown that mismatches between the full and compressed models can be biased towards under-represented classes.
no code implementations • 22 May 2023 • Yannan Nellie Wu, Po-An Tsai, Saurav Muralidharan, Angshuman Parashar, Vivienne Sze, Joel S. Emer
Due to complex interactions among various deep neural network (DNN) optimization techniques, modern DNNs can have weights and activations that are dense or sparse with diverse sparsity degrees.
no code implementations • 31 Aug 2022 • Salar Latifi, Saurav Muralidharan, Michael Garland
Transformer-based neural networks have achieved state-of-the-art task performance in a number of machine learning domains including natural language processing and computer vision.
1 code implementation • 3 Dec 2020 • Vinu Joseph, Shoaib Ahmed Siddiqui, Aditya Bhaskara, Ganesh Gopalakrishnan, Saurav Muralidharan, Michael Garland, Sheraz Ahmed, Andreas Dengel
With the rise in edge-computing devices, there has been an increasing demand to deploy energy and resource-efficient models.
1 code implementation • 6 Nov 2019 • Vinu Joseph, Saurav Muralidharan, Animesh Garg, Michael Garland, Ganesh Gopalakrishnan
Deep neural networks (DNNs) frequently contain far more weights, represented at a higher precision, than are required for the specific task which they are trained to perform.