When dealing with edge devices, diverse power and compute constraints impose tradeoffs among performance, accuracy, and energy requirements during inference. Thus, ensemble learning (multiple ...learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms alone) has been a popular emergent paradigm for accuracy improvement in such scenarios. In cases where powering of the edge devices varies, various ensemble models can be dynamically adopted to obtain the best performance-to-power ratio. This article describes how an agnostic to the base network method can adaptively boost the performance depending on energy availability. -Theocharis Theocharides, University of Cyprus -Muhammad Shafique, Technische Universitat Wien
According to the World Health Organization, "285 million people are estimated to be visually impaired worldwide" 1. Several technologies such as automatic text readers, Braille note makers, and ...navigation assistance canes have been developed to assist the visually impaired. Concurrent advances in computer vision and hardware technologies provide opportunities for a visual-assistance system that can be used in multiple contexts. As part of the Visual Cortex on Silicon program, we have been developing interfaces, algorithms, and hardware platforms to assist the visually impaired with a focus on grocery shopping. This article describes the various features that we have incorporated into this visual-assistance system so that it can be used in multiple contexts.
This article explores the design of high-density, low-power, and high-speed embedded nonvolatile memory arrays exploiting the unique device characteristics of the emerging ferroelectric FETs. - Vivek ...De, Intel Corporation