Fault-Tolerant Neural Network Accelerators With Selective TMR
Timoteo García Bertoa, Giulio Gambardella, Nicholas J. Fraser, Michaela Blott, John McAllister
Abstract
This article presents a tool that analyzes sensitive computations in the neural network and triplicates them to increase the functional safety of the neural network accelerator. —Fei Su, Intel Corporation
Topics & Concepts
Artificial neural networkComputer scienceComputationFault toleranceOperating systemArtificial intelligenceEmbedded systemProgramming languageAdvanced Data Processing TechniquesRadiation Effects in ElectronicsFault Detection and Control Systems