Search Results for author: Alessandro Aimar

Found 2 papers, 0 papers with code

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

no code implementations13 Nov 2017 Moritz B. Milde, Daniel Neil, Alessandro Aimar, Tobi Delbruck, Giacomo Indiveri

Using the ADaPTION tools, we quantized several CNNs including VGG16 down to 16-bit weights and activations with only 0. 8% drop in Top-1 accuracy.

Quantization

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

no code implementations5 Jun 2017 Alessandro Aimar, Hesham Mostafa, Enrico Calabrese, Antonio Rios-Navarro, Ricardo Tapiador-Morales, Iulia-Alexandra Lungu, Moritz B. Milde, Federico Corradi, Alejandro Linares-Barranco, Shih-Chii Liu, Tobi Delbruck

By exploiting sparsity, NullHop achieves an efficiency of 368%, maintains over 98% utilization of the MAC units, and achieves a power efficiency of over 3TOp/s/W in a core area of 6. 3mm$^2$.

Cannot find the paper you are looking for? You can Submit a new open access paper.