progressive stochastic binarization
play

Progressive Stochastic Binarization David Hartmann & Michael - PowerPoint PPT Presentation

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 = 2


  1. Progressive Stochastic Binarization David Hartmann & Michael Wand Institute of Computer Science, Johannes Gutenberg-University of Mainz EMC2 WORKSHOP @ NEURIPS 2019

  2. EMC2 WORKSHOP @ NEURIPS 2019

  3. Stochastic Floats 𝑥 = 𝑡 ⋅ 2 𝑓 ⋅ 𝑛 𝑥 = 𝑡 ⋅ 2 𝑓 ⋅ 1 + 𝐶 𝑞 EMC2 WORKSHOP @ NEURIPS 2019

  4. Dynamic Control of Accuracy Samples of one Average of Results stochastic filter EMC2 WORKSHOP @ NEURIPS 2019

  5. Use with any* Model *Not with Backbone-Batchnorms EMC2 WORKSHOP @ NEURIPS 2019

  6. 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