FAQ: Mitigating the Impact of Faults in the Weight Memory of DNN Accelerators through Fault-Aware Quantization.
Muhammad Abdullah HanifMuhammad ShafiquePublished in: CoRR (2023)
Keyphrases
- fault diagnosis
- fault detection
- fault model
- multiple faults
- fault detection and isolation
- memory requirements
- industrial processes
- fault isolation
- neural network
- expert systems
- main memory
- memory usage
- fault detection and diagnosis
- error detection
- quantization error
- condition monitoring
- computing systems
- normal operation
- test cases
- fault models
- fuzzy logic
- repair actions