ANNETT-O: An Ontology for Describing Artificial Neural Network Evaluation, Topology and Training

TL;DR

ANNETT-O is a comprehensive ontology designed to standardize and facilitate the description, evaluation, and understanding of complex deep neural network configurations, training procedures, and experiments.

Contribution

It introduces a novel, generic, and computer-actionable vocabulary specifically for describing deep learning models, focusing on topology, training, and evaluation aspects.

Findings

Supports complex queries on neural network configurations

Enables better understanding of deep learning experiments

Demonstrated through hypothetical use-cases

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 to the task via a number of hypothetical use-cases of increasing complexity.