most citedNullHop: A Flexible Convolutional Neural Network Accelerator Based on Sparse Representations of Feature Maps

298 citations · 308 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2017★ 8 cited

ADaPTION: Toolbox and Benchmark for Training Convolutional Neural Networks with Reduced Numerical Precision Weights and Activation

Moritz B. Milde, Daniel Neil, Alessandro Aimar +2

Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are useful for many practical tasks in machine learning. Synaptic weights, as well as neuron activation functio…