English

Technical Report: NEMO DNN Quantization for Deployment Model

Machine Learning 2020-04-14 v1 Artificial Intelligence Neural and Evolutionary Computing Machine Learning

Abstract

This technical report aims at defining a formal framework for Deep Neural Network (DNN) layer-wise quantization, focusing in particular on the problems related to the final deployment. It also acts as a documentation for the NEMO (NEural Minimization for pytOrch) framework. It describes the four DNN representations used in NEMO (FullPrecision, FakeQuantized, QuantizedDeployable and IntegerDeployable), focusing in particular on a formal definition of the latter two. An important feature of this model, and in particular the IntegerDeployable representation, is that it enables DNN inference using purely integers - without resorting to real-valued numbers in any part of the computation and without relying on an explicit fixed-point numerical representation.

Keywords

Cite

@article{arxiv.2004.05930,
  title  = {Technical Report: NEMO DNN Quantization for Deployment Model},
  author = {Francesco Conti},
  journal= {arXiv preprint arXiv:2004.05930},
  year   = {2020}
}

Comments

12 pages, technical report

R2 v1 2026-06-23T14:49:20.104Z