Linear multiply-accumulate (MAC) operations have been the main focus of prior efforts in improving the energy efficiency of neural network inference due to their dominant contribution to energy consumption in traditional models. On the other hand, …
For error-resilient applications, such as machine learning and signal processing, a significant improvement in energy efficiency can be achieved by relaxing exactness constraint on output quality. This paper presents a taxonomy of hardware techniques …
From signal processing to emerging deep neural networks, a range of applications exhibit intrinsic error resilience. For such applications, approximate computing opens up new possibilities for energy-efficient computing by producing slightly …
A Reconfigurable Architecture for Varying Emerging Neural Networks.