1 code implementation • 4 Feb 2022 • Lois Orosa, Skanda Koppula, Yaman Umuroglu, Konstantinos Kanellopoulos, Juan Gomez-Luna, Michaela Blott, Kees Vissers, Onur Mutlu
We find that commonly-used low-power CNN inference accelerators based on spatial architectures are not optimized for both of these convolutional kernels.
no code implementations • 11 Nov 2020 • Ussama Zahid, Giulio Gambardella, Nicholas J. Fraser, Michaela Blott, Kees Vissers
Our experiments show that by injecting faults in the convolutional layers during training, highly accurate convolutional neural networks (CNNs) can be trained which exhibits much better error tolerance compared to the original.
no code implementations • 16 Dec 2019 • Giulio Gambardella, Johannes Kappauf, Michaela Blott, Christoph Doehring, Martin Kumm, Peter Zipf, Kees Vissers
In particular, Convolutional Neural Networks (CNNs), are gaining popularity and are evaluated for deployment in safety critical applications such as self driving vehicles.
1 code implementation • 31 May 2019 • Murad Qasaimeh, Kristof Denolf, Jack Lo, Kees Vissers, Joseph Zambreno, Phillip H. Jones
To aid with determining which embedded platform is most suitable for their application, we conduct a comprehensive benchmark of the run-time performance and energy efficiency of a wide range of vision kernels.
1 code implementation • 21 Nov 2018 • Yifan Yang, Qijing Huang, Bichen Wu, Tianjun Zhang, Liang Ma, Giulio Gambardella, Michaela Blott, Luciano Lavagno, Kees Vissers, John Wawrzynek, Kurt Keutzer
DiracDeltaNet achieves competitive accuracy on ImageNet (88. 7\% top-5), but with 42$\times$ fewer parameters and 48$\times$ fewer OPs than VGG16.
no code implementations • 12 Jan 2017 • Nicholas J. Fraser, Yaman Umuroglu, Giulio Gambardella, Michaela Blott, Philip Leong, Magnus Jahre, Kees Vissers
Binarized neural networks (BNNs) are gaining interest in the deep learning community due to their significantly lower computational and memory cost.
4 code implementations • 1 Dec 2016 • Yaman Umuroglu, Nicholas J. Fraser, Giulio Gambardella, Michaela Blott, Philip Leong, Magnus Jahre, Kees Vissers
Research has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values.