# Technical Report: NEMO DNN Quantization for Deployment Model

arXiv: https://arxiv.org/abs/2004.05930 · HTML: https://mlsanity.com/paper/2004.05930/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2020.

## Built on by (most cited first, 5 of 5)

- [ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network](https://mlsanity.com/paper/2103.13740/) (2021)
- [Embedding Temporal Convolutional Networks for Energy-Efficient PPG-Based Heart Rate Monitoring](https://mlsanity.com/paper/2203.04396/) (2022)
- [Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs](https://mlsanity.com/paper/2303.01931/) (2023)
- [OneComp: One-Line Revolution for Generative AI Model Compression](https://mlsanity.com/paper/2603.28845/) (2026)
- [Ultra-low Power Deep Learning-based Monocular Relative Localization Onboard Nano-quadrotors](https://mlsanity.com/paper/2303.01940/) (2023)

## Abstract (arXiv)

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.