Improving the Accuracy and Hardware Efficiency of Neural Networks Using Approximate Multipliers
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F20%3APU134964" target="_blank" >RIV/00216305:26230/20:PU134964 - isvavai.cz</a>
Result on the web
<a href="https://www.fit.vut.cz/research/publication/12066/" target="_blank" >https://www.fit.vut.cz/research/publication/12066/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/TVLSI.2019.2940943" target="_blank" >10.1109/TVLSI.2019.2940943</a>
Alternative languages
Result language
angličtina
Original language name
Improving the Accuracy and Hardware Efficiency of Neural Networks Using Approximate Multipliers
Original language description
Improving the accuracy of a neural network (NN) usually requires using larger hardware that consumes more energy. However, the error tolerance of NNs and their applications allow approximate computing techniques to be applied to reduce implementation costs. Given that multiplication is the most resource-intensive and power-hungry operation in NNs, more economical approximate multipliers (AMs) can significantly reduce hardware costs. In this article, we show that using AMs can also improve the NN accuracy by introducing noise. We consider two categories of AMs: 1) deliberately designed and 2) Cartesian genetic programing (CGP)-based AMs. The exact multipliers in two representative NNs, a multilayer perceptron (MLP) and a convolutional NN (CNN), are replaced with approximate designs to evaluate their effect on the classification accuracy of the Mixed National Institute of Standards and Technology (MNIST) and Street View House Numbers (SVHN) data sets, respectively. Interestingly, up to 0.63% improvement in the classification accuracy is achieved with reductions of 71.45% and 61.55% in the energy consumption and area, respectively. Finally, the features in an AM are identified that tend to make one design outperform others with respect to NN accuracy. Those features are then used to train a predictor that indicates how well an AM is likely to work in an NN.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/LTC18053" target="_blank" >LTC18053: Advanced Methods of Nature-Inspired Optimisation and HPC Implementation for the Real-Life Applications</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
IEEE Trans. on VLSI Systems.
ISSN
1063-8210
e-ISSN
1557-9999
Volume of the periodical
28
Issue of the periodical within the volume
2
Country of publishing house
US - UNITED STATES
Number of pages
12
Pages from-to
317-328
UT code for WoS article
000510674300002
EID of the result in the Scopus database
2-s2.0-85078705685