A Rank Decomposed Statistical Error Compensation Technique for Robust Convolutional Neural Networks in the Near Threshold Voltage Regime

Yingyan Lin, Sai Zhang, Naresh R. Shanbhag

Research output: Contribution to journalArticlepeer-review

Abstract

There has been a growing interest in implementing complex machine learning algorithms such as convolutional neural networks (CNNs) on lower power embedded platforms to enable on-device learning and inference. Many of these platforms are to be deployed as low power sensor nodes with low to medium throughput requirement. Near threshold voltage (NTV) designs are well-suited for these applications but suffer from a significant increase in variations. In this paper, we propose a variation-tolerant architecture for CNNs capable of operating in NTV regime for energy efficiency. A statistical error compensation (SEC) technique referred to as rank decomposed SEC (RD-SEC) is proposed. The key idea is to exploit inherent redundancy within matrix-vector multiplication (or dot product ensemble), a power-hungry operation in CNNs, to derive low-cost estimators for error detection and compensation. When evaluated in CNNs for both the MNIST and CIFAR-10 datasets, simulation results in 45 nm CMOS show that RD-SEC enables robust CNNs operating in the NTV regime. Specifically, the proposed architecture can achieve up to 11 × improvement in variation tolerance and enable up to 113 × reduction in the standard deviation of detection accuracy Pdet while incurring marginal degradation in the median detection accuracy.

Original languageEnglish (US)
Pages (from-to)1439-1451
Number of pages13
JournalJournal of Signal Processing Systems
Volume90
Issue number10
DOIs
StatePublished - Oct 1 2018
Externally publishedYes

Keywords

  • Convolutional neural networks
  • Near threshold voltage regime
  • Rank decomposition
  • Statistical error compensation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Signal Processing
  • Information Systems
  • Modeling and Simulation
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'A Rank Decomposed Statistical Error Compensation Technique for Robust Convolutional Neural Networks in the Near Threshold Voltage Regime'. Together they form a unique fingerprint.

Cite this