1 code implementation • 23 Jun 2023 • Riccardo Schiavone, Francesco Galati, Maria A. Zuluaga
Binary neural networks (BNNs) are an attractive solution for developing and deploying deep neural network (DNN)-based applications in resource constrained devices.
no code implementations • 11 Jul 2022 • Riccardo Schiavone, Maria A. Zuluaga
Our experiments confirm that SBNNs can achieve high compression rates, without compromising generalization, while further reducing the operations of BNNs, making SBNNs a viable option for deploying DNNs in cheap, low-cost, limited-resources IoT devices and sensors.
Ranked #1 on Sparse Learning and binarization on CIFAR-100
no code implementations • 1 Jan 2021 • Riccardo Schiavone, Maria A Zuluaga
Among quantized networks, Binary Neural Networks (BNNs) have reported the largest speed-up.