A dataset-property-based difficulty metric speeds up model selection 6-29 times for few-class tasks and enables smaller models with comparable accuracy.
On the creation of narrow ai: hierarchy and nonlocality of neural network skills.arXiv preprint arXiv:2505.15811,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Neural Network Model Selection for Few-Class Application Datasets
A dataset-property-based difficulty metric speeds up model selection 6-29 times for few-class tasks and enables smaller models with comparable accuracy.