A framework for measuring the training efficiency of a neural architecture
© The Author(s) 2024.
| Veröffentlicht in: | Artificial intelligence review. - 1998. - 57(2024), 12 vom: 23., Seite 349 |
|---|---|
| 1. Verfasser: | |
| Weitere Verfasser: | |
| Format: | Online-Aufsatz |
| Sprache: | English |
| Veröffentlicht: |
2024
|
| Zugriff auf das übergeordnete Werk: | Artificial intelligence review |
| Schlagworte: | Journal Article Deep learning Deep neural networks Efficiency Hyperparameters |
| Zusammenfassung: | © The Author(s) 2024. Measuring Efficiency in neural network system development is an open research problem. This paper presents an experimental framework to measure the training efficiency of a neural architecture. To demonstrate our approach, we analyze the training efficiency of Convolutional Neural Networks and Bayesian equivalents on the MNIST and CIFAR-10 tasks. Our results show that training efficiency decays as training progresses and varies across different stopping criteria for a given neural model and learning task. We also find a non-linear relationship between training stopping criteria, training Efficiency, model size, and training Efficiency. Furthermore, we illustrate the potential confounding effects of overtraining on measuring the training efficiency of a neural architecture. Regarding relative training efficiency across different architectures, our results indicate that CNNs are more efficient than BCNNs on both datasets. More generally, as a learning task becomes more complex, the relative difference in training efficiency between different architectures becomes more pronounced |
|---|---|
| Beschreibung: | Date Revised 01.11.2024 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
| ISSN: | 0269-2821 |
| DOI: | 10.1007/s10462-024-10943-8 |