Improving Learning Performance Through Rational Resource Allocation
Abstract
howrational analysis minimize learning cost for a general class of statistical learning problems. Wc discuss the factors that ence learning cost and show that the problem of efficient learning can cast as optimization problem. Solutions found can more efficient than the best solutions that do not account for these factors. We introduce a heuristic learning algorithm that approximately solves this opti- mization problem and document its performance on synthetic and real-world problems. Machine learning techniques are valuable tools both in scientific and in support of decision making under uncertainty. Unfortunately, involve a significant investment of resources, There maybe monetary cost in obtaining data and computational cost in processing it. Usually such factors rather than a rational analysis of the costs and benefits of alternative learning operations. Thereis a significant learning cost in many diverse appli- cation areas. In speed-up learning there is substantial cost...
Cite
Text
Gratch et al. "Improving Learning Performance Through Rational Resource Allocation." AAAI Conference on Artificial Intelligence, 1994.Markdown
[Gratch et al. "Improving Learning Performance Through Rational Resource Allocation." AAAI Conference on Artificial Intelligence, 1994.](https://mlanthology.org/aaai/1994/gratch1994aaai-improving/)BibTeX
@inproceedings{gratch1994aaai-improving,
title = {{Improving Learning Performance Through Rational Resource Allocation}},
author = {Gratch, Jonathan and Chien, Steve A. and DeJong, Gerald},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {1994},
pages = {576-581},
url = {https://mlanthology.org/aaai/1994/gratch1994aaai-improving/}
}