Towards Dynamic Fault Tolerance for Hardware-Implemented Artificial Neural Networks: A Deep Learning Approach
This addresses fault tolerance for hardware-implemented neural networks, particularly in low-power systems, but is incremental as it builds on existing deep learning methods.
The paper tackles dynamic hardware faults in neural networks by using a deep learning approach, achieving over 2% reduction in test loss compared to a baseline without extra hardware when training epochs are sufficient.
The functionality of electronic circuits can be seriously impaired by the occurrence of dynamic hardware faults. Particularly, for digital ultra low-power systems, a reduced safety margin can increase the probability of dynamic failures. This work investigates a deep learning approach to mitigate dynamic fault impact for artificial neural networks. As a theoretic use case, image compression by means of a deep autoencoder is considered. The evaluation shows a linear dependency of the test loss to the fault injection rate during testing. If the number of training epochs is sufficiently large, our approach shows more than 2% reduction of the test loss compared to a baseline network without the need of additional hardware. At the absence of faults during testing, our approach also decreases the test loss compared to reference networks.