Meeting the Latency and Energy Constraints on Timing-critical Edge-AI Systems

Smart devices, with AI capabilities, at the edge have demonstrated impressive application results. The current trend in video/image analysis is to increase its resolution and classification accuracy. Moreover, computing object detection and classification tasks at the edge require both low latency and high-energy efficiency for these new devices. In this paper, we will explore a novel architectural approach to overcome such limitations by using the attention mechanism of the human brain. The latter allows humans to selectively analyze the scene allowing limiting the spent energy.