1 citations · 1 across the 2 of their papers we have counts for
3 papers · 1 filter
QoS-Nets: Adaptive Approximate Neural Network Inference
Elias Trommer, Bernd Waschneck, Akash Kumar
In order to vary the arithmetic resource consumption of neural network applications at runtime, this work proposes the flexible reuse of approximate multipliers for neural network…
Temporal Decisions: Leveraging Temporal Correlation for Efficient Decisions in Early Exit Neural Networks
Max Sponner, Lorenzo Servadei, Bernd Waschneck +2
Deep Learning is becoming increasingly relevant in Embedded and Internet-of-things applications. However, deploying models on embedded devices poses a challenge due to their resour…
Efficient Post-Training Augmentation for Adaptive Inference in Heterogeneous and Distributed IoT Environments
Max Sponner, Lorenzo Servadei, Bernd Waschneck +2
Early Exit Neural Networks (EENNs) present a solution to enhance the efficiency of neural network deployments. However, creating EENNs is challenging and requires specialized domai…