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 brought levels beyond human accuracy in many tasks, but at the cost of high computational complexity. To enable efficient execution of...

Full description

Saved in:
Bibliographic Details
Published in:ACM computing surveys 2022-11, Vol.55 (4), p.1-36, Article 83
Main Authors: Armeniakos, Giorgos, Zervakis, Georgios, Soudris, Dimitrios, Henkel, Jörg
Format: Article
Language:English
Subjects:
Accelerators
Accuracy
Approximation
Architectures
Artificial neural networks
Cognitive tasks
Computer science
Computer systems organization
Computing methodologies
General and reference
Hardware
Inference
Logic circuits
Machine learning
Mathematical analysis
Neural networks
Surveys and overviews
Task complexity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 brought levels beyond human accuracy in many tasks, but at the cost of high computational complexity. To enable efficient execution of DNN inference, more and more research works, therefore, are exploiting the inherent error resilience of DNNs and employing Approximate Computing (AC) principles to address the elevated energy demands of DNN accelerators. This article provides a comprehensive survey and analysis of hardware approximation techniques for DNN accelerators. First, we analyze the state of the art, and by identifying approximation families, we cluster the respective works with respect to the approximation type. Next, we analyze the complexity of the performed evaluations (with respect to the dataset and DNN size) to assess the efficiency, potential, and limitations of approximate DNN accelerators. Moreover, a broad discussion is provided regarding error metrics that are more suitable for designing approximate units for DNN accelerators as well as accuracy recovery approaches that are tailored to DNN inference. Finally, we present how Approximate Computing for DNN accelerators can go beyond energy efficiency and address reliability and security issues as well.
ISSN:0360-0300
1557-7341
DOI:10.1145/3527156