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

@article{Klampanos2019ANNETTOAO,
  title={ANNETT-O: An Ontology for Describing Artificial Neural Network Evaluation, Topology and Training},
  author={I. Klampanos and A. Davvetas and A. Koukourikos and V. Karkaletsis},
  journal={ArXiv},
  year={2019},
  volume={abs/1804.02528}
}
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… Expand
4 Citations

References

SHOWING 1-10 OF 14 REFERENCES
Learning Deep Architectures for AI
Neural Models for Information Retrieval
The Semantic Web
Generative Adversarial Nets
KNIME: The Konstanz Information Miner
The management and mining of multiple predictive models using the predictive modeling markup language
Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting
Comprehensive PMML preprocessing in KNIME
Adversarial Autoencoders
...
1
2
...