← Search

Fabrizio Pedersoli

2 accepted papers

2018

Espresso: Efficient Forward Propagation for Binary Deep Neural Networks

ICLR 2018poster

There are many applications scenarios for which the computational performance and memory footprint of the prediction phase of Deep Neural Networks (DNNs) need to be optimized. Binary Deep Neural Networks (BDNNs) have been shown to be an effective way of achieving this objective. In this pape…