Login / Signup

Accelerating Spike-by-Spike Neural Networks on FPGA With Hybrid Custom Floating-Point and Logarithmic Dot-Product Approximation.

Yarib NevarezDavid RotermundKlaus R. PawelzikAlberto García Ortiz
Published in: IEEE Access (2021)
Keyphrases
  • floating point
  • neural network
  • dot product
  • fixed point
  • floating point arithmetic
  • machine learning
  • hardware implementation
  • query processing
  • nearest neighbor
  • low cost
  • kernel function
  • gaussian kernels
  • instruction set