Formal description of ML models for unambiguous implementation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gauffriau, Adrien, Silva, Iryna De Albuquerque, Pagetti, Claire
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909225629777920
author Gauffriau, Adrien
Silva, Iryna De Albuquerque
Pagetti, Claire
author_facet Gauffriau, Adrien
Silva, Iryna De Albuquerque
Pagetti, Claire
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2307_12713
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Formal description of ML models for unambiguous implementation
Gauffriau, Adrien
Silva, Iryna De Albuquerque
Pagetti, Claire
Neural and Evolutionary Computing
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.
title Formal description of ML models for unambiguous implementation
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2307.12713