all AI news
SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget. (arXiv:2401.16757v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
Executing deep neural networks (DNNs) on edge artificial intelligence (AI)
devices enables various autonomous mobile computing applications. However, the
memory budget of edge AI devices restricts the number and complexity of DNNs
allowed in such applications. Existing solutions, such as model compression or
cloud offloading, reduce the memory footprint of DNN inference at the cost of
decreased model accuracy or autonomy. To avoid these drawbacks, we divide DNN
into blocks and swap them in and out in order, such that …
applications artificial artificial intelligence arxiv autonomous beyond budget cloud complexity compression computing cs.lg devices dnn edge edge ai inference intelligence memory mobile mobile computing networks neural networks solutions