Using Convolutional Neural Networks for fault analysis and alleviation in accelerator systems
This addresses hardware reliability issues in accelerator systems for safety-critical domains, but appears incremental as it builds on existing neural network applications.
The paper tackles hardware failures in accelerator systems used for time-critical applications like self-driving cars and medical diagnosis, proposing an efficient method to avoid these failures with minimal hardware overhead based on critical results for system reliability enhancement.
Today, Neural Networks are the basis of breakthroughs in virtually every technical domain. Their application to accelerators has recently resulted in better performance and efficiency in these systems. At the same time, the increasing hardware failures due to the latest (shrinked) semiconductor technology needs to be addressed. Since accelerator systems are often used to back time-critical applications such as self-driving cars or medical diagnosis applications, these hardware failures must be eliminated. Our research evaluates these failures from a systemic point of view. Based on our results, we find critical results for the system reliability enhancement and we further put forth an efficient method to avoid these failures with minimal hardware overhead.