Prost-Boucle (A.) et Petrot (F.).-Ternary neural networks for resource-efficient AI applications, International Joint Conference on Neural Networks (IJCNN), pp.2547-2554, 2017. ,
, ).-Multi-precision convolutional neural networks on heterogeneous hardware, Design Automation and Test in Europe, 2018.
, ).-YodaNN : An ultra-low power convolutional neural network accelerator based on binary weights, Annual Symposium on VLSI, pp.236-241, 2016.
, GPU computing : To exascale and beyond, SuperComputing, 2010.
Universal codeword sets and representations of the integers, Transactions on Information Theory, vol.21, pp.194-203, 1975. ,
DOI : 10.1109/tit.1975.1055349
, The End of Error : Unum Computing
, Gambardella (G.), Fraser (N.) et Blott (M.).-Inference of quantized neural networks on heterogeneous all-programmable devices.-In Design Automation and Test in Europe (DATE), 2018.
Unums 2.0 : An Interview with, John L. Gustafson. Ubiquity, vol.1, pp.1-1, 2016. ,
DOI : 10.1145/3001758
URL : http://dl.acm.org/ft_gateway.cfm?id=3001758&type=pdf
An easy programming system. BYTE magazine, décembre 1978, pp.108-122 ,