ANNETT-O: an ontology for describing artificial neural network evaluation, topology and training. (18th May 2019)

• Record Type: Journal Article
• Authors: Klampanos, Iraklis A.; Davvetas, Athanasios; Koukourikos, Antonis; Karkaletsis, Vangelis
• Is Part Of: International journal of metadata, semantics and ontologies. Volume 13:Number 3(2019)
• Page Start: 179
• Page End: 190
• Publication Date: 2019-05-18
• Subjects: ontologies -- deep learning -- artificial intelligence -- semantic web -- data schemas -- OWL -- algorithm concepts; Metadata -- Periodicals; Semantic Web -- Periodicals; Ontologies (Information retrieval) -- Periodicals; Data structures (Computer science) -- Periodicals; Information theory -- Periodicals; 005.74
• Languages: English
• ISSNs: 1744-2621

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.