Publication detail

Improving the Accuracy and Hardware Efficiency of Neural Networks Using Approximate Multipliers

ANSARI, M. MRÁZEK, V. COCKBURN, B. SEKANINA, L. VAŠÍČEK, Z. HAN, J.

Original Title

Improving the Accuracy and Hardware Efficiency of Neural Networks Using Approximate Multipliers

English Title

Improving the Accuracy and Hardware Efficiency of Neural Networks Using Approximate Multipliers

Type

journal article in Web of Science

Language

en

Original Abstract

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.

English abstract

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.

Keywords

approximate multipliers, Cartesian genetic programming, convolutional neural network, multi-layer perceptron, neural networks

Released

22.01.2020

Publisher

NEUVEDEN

Location

NEUVEDEN

Pages from

317

Pages to

328

Pages count

12

URL

BibTex


@article{BUT161464,
  author="Vojtěch {Mrázek} and Lukáš {Sekanina} and Zdeněk {Vašíček}",
  title="Improving the Accuracy and Hardware Efficiency of Neural Networks Using Approximate Multipliers",
  annote="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.",
  address="NEUVEDEN",
  chapter="161464",
  doi="10.1109/TVLSI.2019.2940943",
  edition="NEUVEDEN",
  howpublished="online",
  institution="NEUVEDEN",
  number="2",
  volume="28",
  year="2020",
  month="january",
  pages="317--328",
  publisher="NEUVEDEN",
  type="journal article in Web of Science"
}