# Formal description of ML models for unambiguous implementation

arXiv: https://arxiv.org/abs/2307.12713 · HTML: https://mlsanity.com/paper/2307.12713/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2023.

## Built on by (most cited first, 2 of 2)

- [Implementation of airborne ML models with semantics preservation](https://mlsanity.com/paper/2509.18681/) (2025)
- [Towards On-Board Implementation of ML-Based Helicopter Weight Estimator](https://mlsanity.com/paper/2608.19210/) (2026)

## Abstract (arXiv)

Implementing deep neural networks in safety critical systems, in particular in the aeronautical domain, will require to offer adequate specification paradigms to preserve the semantics of the trained model on the final hardware platform. We propose to extend the nnef language in order to allow traceable distribution and parallelisation optimizations of a trained model. We show how such a specification can be implemented in cuda on a Xavier platform.