no code implementations • 26 Jun 2022 • HyunJin Kim, Jungwoo Shin, Alberto A. Del Barrio
In each quantization step, the trained weights of a model are used to initialize the weights of the next model with the quantization bit depth reduced by one.
1 code implementation • 18 Feb 2021 • Raul Murillo, Alberto A. Del Barrio, Guillermo Botella, Min Soo Kim, HyunJin Kim, Nader Bagherzadeh
The Posit Number System was introduced in 2017 as a replacement for floating-point numbers.
1 code implementation • 20 Jul 2020 • Min Soo Kim, Alberto A. Del Barrio, HyunJin Kim, Nader Bagherzadeh
The approximate multiplication can reduce the cost of the underlying circuits so that CNN inferences can be performed more efficiently in hardware accelerators.
1 code implementation • 1 Jul 2020 • Raul Murillo, Alberto A. Del Barrio, Guillermo Botella
The Posit Number System (PNS) was introduced by John L. Gustafson in 2017.
1 code implementation • 9 Jul 2019 • Raúl Murillo Montero, Alberto A. Del Barrio, Guillermo Botella
Synthesis results are shown to compare with the floating point multiplication offered by FloPoCo as well.