Edge Computing
Edge computing focuses on processing data closer to its source, minimizing latency and bandwidth usage for applications like autonomous driving and IoT. Current research emphasizes efficient resource allocation strategies, often employing large language models (LLMs) and reinforcement learning algorithms to optimize task scheduling and model deployment on resource-constrained edge devices, including the use of spiking neural networks and implicit neural representations for improved efficiency. This field is significant for enabling real-time, privacy-preserving AI applications across diverse sectors, driving advancements in both hardware and software architectures for distributed computing.
Papers
Latency optimized Deep Neural Networks (DNNs): An Artificial Intelligence approach at the Edge using Multiprocessor System on Chip (MPSoC)
Seyed Nima Omidsajedi, Rekha Reddy, Jianming Yi, Jan Herbst, Christoph Lipps, Hans Dieter Schotten
Spike Talk: Genesis and Neural Coding Scheme Translations
Subham Sahoo
Exploiting Heterogeneity in Timescales for Sparse Recurrent Spiking Neural Networks for Energy-Efficient Edge Computing
Biswadeep Chakraborty, Saibal Mukhopadhyay
AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing
Tong Zhou, Jiahui Zhao, Yukui Luo, Xi Xie, Wujie Wen, Caiwen Ding, Xiaolin Xu