Hardware approximate techniques for deep neural network accelerators: A survey
Deep Neural Networks (DNNs) are very popular because of their high performance in
various cognitive tasks in Machine Learning (ML). Recent advancements in DNNs have …
various cognitive tasks in Machine Learning (ML). Recent advancements in DNNs have …
ALWANN: Automatic layer-wise approximation of deep neural network accelerators without retraining
The state-of-the-art approaches employ approximate computing to reduce the energy
consumption of DNN hardware. Approximate DNNs then require extensive retraining …
consumption of DNN hardware. Approximate DNNs then require extensive retraining …
Deep neural network approximation for custom hardware: Where we've been, where we're going
Deep neural networks have proven to be particularly effective in visual and audio
recognition tasks. Existing models tend to be computationally expensive and memory …
recognition tasks. Existing models tend to be computationally expensive and memory …
[图书][B] Efficient processing of deep neural networks
This book provides a structured treatment of the key principles and techniques for enabling
efficient processing of deep neural networks (DNNs). DNNs are currently widely used for …
efficient processing of deep neural networks (DNNs). DNNs are currently widely used for …
Weight-oriented approximation for energy-efficient neural network inference accelerators
ZG Tasoulas, G Zervakis… - … on Circuits and …, 2020 - ieeexplore.ieee.org
Current research in the area of Neural Networks (NN) has resulted in performance
advancements for a variety of complex problems. Especially, embedded system applications …
advancements for a variety of complex problems. Especially, embedded system applications …
[图书][B] Ristretto: Hardware-oriented approximation of convolutional neural networks
PM Gysel - 2016 - search.proquest.com
Convolutional neural networks (CNN) have achieved major breakthroughs in recent years.
Their performance in computer vision have matched and in some areas even surpassed …
Their performance in computer vision have matched and in some areas even surpassed …
A^ 3: Accelerating attention mechanisms in neural networks with approximation
With the increasing computational demands of the neural networks, many hardware
accelerators for the neural networks have been proposed. Such existing neural network …
accelerators for the neural networks have been proposed. Such existing neural network …
Cnvlutin: Ineffectual-neuron-free deep neural network computing
This work observes that a large fraction of the computations performed by Deep Neural
Networks (DNNs) are intrinsically ineffectual as they involve a multiplication where one of …
Networks (DNNs) are intrinsically ineffectual as they involve a multiplication where one of …
A survey on the optimization of neural network accelerators for micro-ai on-device inference
Deep neural networks (DNNs) are being prototyped for a variety of artificial intelligence (AI)
tasks including computer vision, data analytics, robotics, etc. The efficacy of DNNs coincides …
tasks including computer vision, data analytics, robotics, etc. The efficacy of DNNs coincides …
Proteus: Exploiting numerical precision variability in deep neural networks
P Judd, J Albericio, T Hetherington… - Proceedings of the …, 2016 - dl.acm.org
This work exploits the tolerance of Deep Neural Networks (DNNs) to reduced precision
numerical representations and specifically, their recently demonstrated ability to tolerate …
numerical representations and specifically, their recently demonstrated ability to tolerate …