![]() Deep reinforcement learning for autonomous driving: a survey. On the potential of recording earthquakes for global seismic tomography by low-cost autonomous instruments in the oceans. Deep learning for smart manufacturing: methods and applications. TinyML as-a-Service: What is it and what does it mean for the IoT Edge? Ericsson (2019). ![]() Wireless network intelligence at the edge. Deep learning and process understanding for data-driven Earth system science. Mastering the game of Go with deep neural networks and tree search. Our method paves the way for deploying tiny artificial intelligence in many scientific and industrial applications. We demonstrate it on low-cost hardware, whereby the computation is accelerated by >180× and the energy consumption is reduced by ~10×. As validated on different models and datasets, it attains substantial memory reduction of ~50–90× (16-bits quantization), compared with fully connected DNNs. We build a universal compressing-while-training framework that directly learns a compact model and, most importantly, enables computationally efficient on-device learning. Here we report an architecture named random sketch learning, or Rosler, for computationally efficient tiny artificial intelligence. Current lightweight DNNs, achieved by high-dimensional space pre-training and post-compression, present challenges when covering the resources deficit, making tiny artificial intelligence hard to be implemented. Despite the great potential of deep neural networks (DNNs), they require massive weights and huge computational resources, creating a vast gap when deploying artificial intelligence at low-cost edge devices. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |