Blar i NTNU Open på forfatter "Lin, Qian"
-
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
Kong, Hao; Liu, Di; Huai, Shuo; Luo, Xiangzhong; Subramaniam, Ravi; Makaya, Christian; Lin, Qian; Liu, Weichen (Peer reviewed; Journal article, 2023) -
Latency-constrained DNN architecture learning for edge systems using zerorized batch normalization
Huai, Shuo; Liu, Di; Kong, Hao; Liu, Weichen; Subramaniam, Ravi; Makaya, Christian; Lin, Qian (Journal article; Peer reviewed, 2022)Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers. Deciding the number of neurons during the design of a deep neural network to ... -
On Hardware-Aware Design and Optimization of Edge Intelligence
Huai, Shuo; Kong, Hao; Luo, Xiangzhong; Liu, Di; Subramaniam, Ravi; Makaya, Christian; Lin, Qian; Liu, Weichen (Journal article; Peer reviewed, 2023)In this article, the authors explore recent efforts in hardware-aware design and optimization for edge intelligence. The article focuses on techniques such as model compression and neural architecture search to enhance ...