Joon Kyung Kim,Byung Hoon Ahn,Sean Kinzer et al.
Joon Kyung Kim et al.
FPGA accelerators offer performance and efficiency gains by narrowing the scope of acceleration to one algorithmic domain. However, real-life applications are often not limited to a single domain, which naturally makes Cross-Domain Multi-Ac...
ReLeQ : A Reinforcement Learning Approach for Automatic Deep Quantization of Neural Networks [0.03%]
基于强化学习的神经网络自动深度量化方法
Ahmed T Elthakeb,Prannoy Pilligundla,Fatemehsadat Mireshghallah et al.
Ahmed T Elthakeb et al.
Deep Quantization (below eight bits) can significantly reduce the DNN computation and storage by decreasing the bitwidth of network encodings. However, without arduous manual effort, this deep quantization can lead to significant accuracy l...