Winograd Convolution: A Perspective from Fault Tolerance
This work addresses fault tolerance in neural networks for energy-efficient and reliable processing, but it is incremental as it applies an existing method to a new aspect.
The paper tackles the problem of improving neural network fault tolerance by leveraging Winograd convolution, originally used for computational efficiency, and demonstrates that it can reduce fault-tolerant design overhead by 27.49% or energy consumption by 7.19% without accuracy loss.
Winograd convolution is originally proposed to reduce the computing overhead by converting multiplication in neural network (NN) with addition via linear transformation. Other than the computing efficiency, we observe its great potential in improving NN fault tolerance and evaluate its fault tolerance comprehensively for the first time. Then, we explore the use of fault tolerance of winograd convolution for either fault-tolerant or energy-efficient NN processing. According to our experiments, winograd convolution can be utilized to reduce fault-tolerant design overhead by 27.49\% or energy consumption by 7.19\% without any accuracy loss compared to that without being aware of the fault tolerance