Overcoming Computational Errors in Sensing Platforms Through Embedded Machine-Learning Kernels

Overcoming Computational Errors in Sensing Platforms Through Embedded Machine-Learning Kernels

Abstract— Overcoming Computational Errors in Sensing Platforms Through Embedded Machine-Learning Kernels. We present an approach for overcoming computational errors at run time that originate from static hardware faults in digital processors. The approach is based on embedded machine-learning stages that learn and model the statistics of the computational outputs in the presence of errors, resulting in an error-aware model for embedded analysis. We demonstrate, in hardware, two systems for analyzing sensor data:1) an EEG-based seizure detector and 2) an ECG-based cardiac arrhythmia detector. The systems use a small kernel of fault-free hardware (constituting <7.0% and <31% of the total areas respectively) to construct and apply the error-aware model. The systems construct their own error-aware models with minimal overhead through the use of an embedded active learning framework. Via an field-programmable gate array implementation for hardware experiments, stuck-at faults are injected at controllable rates within synthesized gate-level netlists to permit characterization. The seizure detector demonstrates restored performance despite faults on 0.018% of the circuit nodes [causing bit error rates < Final Year Projects 2016 > up to 45%], and the arrhythmia detector demonstrates restored performance despite faults on 2.7% of the circuit nodes (causing BERs up to 50%).We show that thanks to flexible data-driven modeling, the performance of DDHR is ultimately limited by the mutual information (MI) exhibited by the error-affected data, rather than bit-error metrics. MI is a fundamental information metric derived from the Shannon entropy that measures how much information is shared between two variables (in this case, the error-affected data and the system output).