Abstract: A method or apparatus that combines properties of parallel distribution and flexibility of distribution of convolutional neural networks on heterogeneous devices uses parallelization for distributed inference of Deep Neural Networks. The method addresses parallel distribution among various numbers of devices of various capacities. A network is distributed in parallel for each configuration and is adaptive to different network capabilities.

Abstract: The proposed approach deals with efficient transmission for distributed AI with a provision to switch among multiple bandwidths. During the distributed inference at edge devices, each device needs to load part of the AI model only once, but the input/output features communicated between them can be flexibly configured depending on the available transmission bandwidth by enabling/disabling connection between nodes in the Dynamic feature size Switch (DySw). When some nodes are connected or disconnected in order to achieve the desired compression factor, other parameters of the DNN remain the same. That is, the same DNN model is used for different compression factors, and no new DNN model needs to be downloaded to adapt to the compression factor or the network bandwidth.

Abstract: The present invention relates to a pre-moistened wipe for treating a surface, said pre-moistened wipe comprising: (a) a substrate having a plurality of abrasive means applied thereon, wherein the material forming the abrasive means has a Vickers hardness HV of at least 3 kg/mm2 and wherein said abrasive means is a three-dimensional structure having an exposed surface area of at least 0.1 mm2/abrasive means; and (b) a lotion applied to said substrate.