2019 · 43 citations · 16 references
EngineeringComputer EngineeringElectrical EngineeringFault ToleranceFault-tolerant ComputingFault-tolerant SystemsCrossbar NetworksFault DetectionHardware Fault ToleranceMemory DevicesMemristive MaterialsClassification AccuracyClassification Accuracy AnalysisMatrix MultiplicationMemristive CircuitsMemristive Crossbar ArraysMemristive MemoryPower ConsumptionTransformations
Matrix-vector multiplication is the dominating computational workload in the inference phase of neural networks. Memristor crossbar arrays (MCAs) can inherently execute matrix-vector multiplication with low latency and small power consumption. A key challenge is that the classification accuracy may be severely degraded by stuck-at-fault defects. Earlier studies have shown that the accuracy loss can be recovered by retraining each neural network or by utilizing additional hardware. In this paper, we propose to handle stuck-at-faults using matrix transformations. A transformation T changes a weight matrix W into a weight matrix, @ = T(W), which is more robust to stuck-at-faults. In particular, we propose a row flipping transformation, a permutation transformation, and a value range transformation. The row flipping transformation results in that stuck-off (stuck-on) faults are translated into stuck-on (stuck-off) faults. The permutation transformation maps small (large) weights to memristors stuck-off (stuck-on). The value range transformation is based on reducing the magnitude of the smallest and largest elements in the matrix, which results in that each stuck-at-fault introduces an error of smaller magnitude. The experimental results demonstrate that the proposed framework is capable of recovering 99% of the accuracy loss introduced by stuck-at-faults without requiring the neural network to be retrained.
16
Memristor-The missing circuit element
Leon O. Chua · IEEE Transactions on Circuit Theory · 1971 · 10K citations
Dot-product engine for neuromorphic computing
Miao Hu, John Paul Strachan, Zhiyong Li et al. · 2016 · 678 citations
Rescuing Memristor-based Neuromorphic Design with High Defects
Chenchen Liu, Miao Hu, John Paul Strachan et al. · 2017 · 255 citations · Full text
Engineering, Computer Engineering, Electrical Engineering +15