{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/annett-o-an-ontology-for-describing","title":"ANNETT-O: An Ontology for Describing Artificial Neural Network Evaluation, Topology and Training","arxiv_id":"1804.02528","date":"2018-04-07","proceeding":null,"authors":["Iraklis A. Klampanos","Athanasios Davvetas","Antonis Koukourikos","Vangelis Karkaletsis"],"abstract":"Deep learning models, while effective and versatile, are becoming\nincreasingly complex, often including multiple overlapping networks of\narbitrary depths, multiple objectives and non-intuitive training methodologies.\nThis makes it increasingly difficult for researchers and practitioners to\ndesign, train and understand them. In this paper we present ANNETT-O, a\nmuch-needed, generic and computer-actionable vocabulary for researchers and\npractitioners to describe their deep learning configurations, training\nprocedures and experiments. The proposed ontology focuses on topological,\ntraining and evaluation aspects of complex deep neural configurations, while\nkeeping peripheral entities more succinct. Knowledge bases implementing\nANNETT-O can support a wide variety of queries, providing relevant insights to\nusers. In addition to a detailed description of the ontology, we demonstrate\nits suitability to the task via a number of hypothetical use-cases of\nincreasing complexity.","url_abs":"http://arxiv.org/abs/1804.02528v2","url_pdf":"http://arxiv.org/pdf/1804.02528v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"annett-o-an-ontology-for-describing","repo_url":"https://github.com/davidath/evitrac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}