Filters








3 Hits in 1.7 sec

CascadeCNN: Pushing the performance limits of quantisation [article]

Alexandros Kouris, Stylianos I. Venieris, Christos-Savvas Bouganis
2018 arXiv   pre-print
This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, to perform high-throughput inference by exploiting the computation time-accuracy trade-off  ...  Experiments demonstrate that CascadeCNN achieves a performance boost of up to 55% for VGG-16 and 48% for AlexNet over the baseline design for the same resource budget and accuracy.  ...  In this paper, we propose CascadeCNN, a novel automated approach of pushing the performance of precision-quantised CNN models under the same resource budget, with negligible accuracy loss.  ... 
arXiv:1805.08743v1 fatcat:dyalnovqhbgehm2qrohh2nyxbi

CascadeCNN: Pushing the Performance Limits of Quantisation in Convolutional Neural Networks [article]

Alexandros Kouris, Stylianos I. Venieris, Christos-Savvas Bouganis
2018 arXiv   pre-print
This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, aiming to perform high-throughput inference.  ...  need of retraining the model or accessing the training data.  ...  ACKNOWLEDGMENT The support of the EPSRC Centre for Doctoral Training in High Performance Embedded and Distributed Systems (HiPEDS, Grant Reference EP/L016796/1) is gratefully acknowledged.  ... 
arXiv:1807.05053v1 fatcat:bn3sz2ewgjgfrgsmpzymnfmk5y

Deploying Deep Neural Networks in the Embedded Space [article]

Stylianos I. Venieris, Alexandros Kouris, Christos-Savvas Bouganis
2018 arXiv   pre-print
In the era of IoT and mobile systems, the efficient deployment of DNNs on embedded platforms is vital to enable the development of intelligent applications.  ...  By covering such diverse topics as DNN-to-accelerator toolflows, high-throughput cascaded classifiers and domain-specific model design, the presented set of works aim to enable the deployment of sophisticated  ...  CascadeCNN's Approach CacsadeCNN [10, 11] introduces an automated toolflow for generating a high-throughput cascade of CNN classifiers that pushes the performance of precision-quantised CNNs.  ... 
arXiv:1806.08616v1 fatcat:52xugpvnkzeuloufnsfp673oo4