Progressive Stochastic Binarization David Hartmann & Michael Wand Institute of Computer Science, Johannes Gutenberg-University of Mainz EMC2 WORKSHOP @ NEURIPS 2019
EMC2 WORKSHOP @ NEURIPS 2019
Stochastic Floats 𝑥 = 𝑡 ⋅ 2 𝑓 ⋅ 𝑛 𝑥 = 𝑡 ⋅ 2 𝑓 ⋅ 1 + 𝐶 𝑞 EMC2 WORKSHOP @ NEURIPS 2019
Dynamic Control of Accuracy Samples of one Average of Results stochastic filter EMC2 WORKSHOP @ NEURIPS 2019
Use with any* Model *Not with Backbone-Batchnorms EMC2 WORKSHOP @ NEURIPS 2019
Computational Attention Approximation Error: blue = smaller error ResNet50v2: Input Layer 8 Layer 9 (after skip) Last Conv Layer EMC2 WORKSHOP @ NEURIPS 2019
Recommend
More recommend