Training Connectionist Networks with Queries and Selective Sampling
Abstract
"Selective sampling" is a form of directed search that can greatly increase the ability of a connectionist network to generalize accu(cid:173) rately. Based on information from previous batches of samples, a network may be trained on data selectively sampled from regions in the domain that are unknown. This is realizable in cases when the distribution is known, or when the cost of drawing points from the target distribution is negligible compared to the cost of label(cid:173) ing them with the proper classification. The approach is justified by its applicability to the problem of training a network for power system security analysis. The benefits of selective sampling are studied analytically, and the results are confirmed experimentally.
Cite
Text
Atlas et al. "Training Connectionist Networks with Queries and Selective Sampling." Neural Information Processing Systems, 1989.Markdown
[Atlas et al. "Training Connectionist Networks with Queries and Selective Sampling." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/atlas1989neurips-training/)BibTeX
@inproceedings{atlas1989neurips-training,
title = {{Training Connectionist Networks with Queries and Selective Sampling}},
author = {Atlas, Les E. and Cohn, David A. and Ladner, Richard E.},
booktitle = {Neural Information Processing Systems},
year = {1989},
pages = {566-573},
url = {https://mlanthology.org/neurips/1989/atlas1989neurips-training/}
}