Answers are grounded in this paper and cite their sources.
We investigate the problem of selecting an informative subsample out of a neural network's training data. Using the replica method of statistical mechanics, we calculate the performance of a heuristic selection algorithm for a linear neural network which avoids overfitting.
No takes yet. Share an insight, caveat, or question.
Jung et al. (1996) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: