Outlier-aware Time-multiplexing MAC for Higher Energy-Efficiency on CNNs

Convolutional neural networks (CNNs) are computationally intensive, and deep learning hardware should be implemented energy-efficiently for embedded systems or battery-constrained systems. In this paper, we propose an outlier-aware time-multiplexing MAC. We exploit a CNN feature maps' characteristic of being able to express most of the data in a low bit-width except a few large values, which we call `outliers' Our outlier-aware time-multiplexing MAC has improved the energy efficiency by up to 21.1% compared to conventional MACs.