Error Adaptive Classifier Boosting (EACB): Leveraging Data-Driven Training Towards Hardware Resilience for Signal Inference

Research output: Contribution to journalArticlepeer-review

25 Scopus citations

Abstract

The continued scaling of CMOS technologies and consideration of post-CMOS technologies has elevated hardware reliability to a first-class challenge, particularly in energy- and resource-constrained embedded sensor applications. In such applications, there is an increasing emphasis on inference functions. Machine-learning algorithms play an important role by enabling the construction of data-driven models for inference over data that is too complex to model analytically. This paper explores how data-driven training can be exploited to also overcome computational errors due to hardware faults within an inference stage. FPGA emulation with randomized fault injections shows that the proposed architecture restores system performance to the level of a fault free system, with <1% of the hardware requiring explicit fault protection, and with digital faults affecting >2% of the circuit nodes in the rest of the hardware. To train an error-aware inference model, a training algorithm is presented whose hardware (memory) and energy requirements are reduced by 65 x and 10 x compared to previously reported algorithms (AdaBoost and FilterBoost respectively), thereby enabling model construction entirely on the device.

Original languageEnglish (US)
Article number7070874
Pages (from-to)1136-1145
Number of pages10
JournalIEEE Transactions on Circuits and Systems I: Regular Papers
Volume62
Issue number4
DOIs
StatePublished - Apr 1 2015

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Error Adaptive Classifier Boosting (EACB): Leveraging Data-Driven Training Towards Hardware Resilience for Signal Inference'. Together they form a unique fingerprint.

Cite this