Title: ANNETT-O: an ontology for describing artificial neural network evaluation, topology and training

Authors: Iraklis A. Klampanos; Athanasios Davvetas; Antonis Koukourikos; Vangelis Karkaletsis

Addresses: National Centre for Scientific Research "Demokritos", Agia Paraskevi, Greece ' National Centre for Scientific Research "Demokritos", Agia Paraskevi, Greece ' National Centre for Scientific Research "Demokritos", Agia Paraskevi, Greece ' National Centre for Scientific Research "Demokritos", Agia Paraskevi, Greece

Abstract: Deep learning models, while effective and versatile, are becoming increasingly complex, often including multiple overlapping networks of arbitrary depths, multiple objectives and non-intuitive training methodologies. This makes it increasingly difficult for researchers and practitioners to design, train and understand them. In this paper, we present ANNETT-O, a much-needed, generic and computer-actionable vocabulary for researchers and practitioners to describe their deep learning configurations, training procedures and experiments. The proposed ontology focuses on topological, training and evaluation aspects of complex deep neural configurations, while keeping peripheral entities more succinct. Knowledge bases implementing ANNETT-O can support a wide variety of queries, providing relevant insights to users. In addition to a detailed description of the ontology, we demonstrate its suitability for the task via a number of hypothetical use-cases of increasing complexity.

Keywords: ontologies; deep learning; artificial intelligence; semantic web; data schemas; OWL; algorithm concepts.

DOI: 10.1504/IJMSO.2019.099833

International Journal of Metadata, Semantics and Ontologies, 2019 Vol.13 No.3, pp.179 - 190

Received: 14 Jun 2018
Accepted: 09 Jan 2019

Published online: 23 May 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article