2 papers
cs.LG2021
MOHAQ: Multi-Objective Hardware-Aware Quantization of Recurrent Neural Networks
Nesma M. Rezk, Tomas Nordström, Dimitrios Stathis +3
The compression of deep learning models is of fundamental importance in deploying such models to edge devices. The selection of compression parameters can be automated to meet chan…
cs.NE2019
Recurrent Neural Networks: An Embedded Computing Perspective
Nesma M. Rezk, Madhura Purnaprajna, Tomas Nordström +1
Recurrent Neural Networks (RNNs) are a class of machine learning algorithms used for applications with time-series and sequential data. Recently, there has been a strong interest i…