A note about the generalisation of the C-tests
Artificial Intelligence
2015-03-27 v2
Abstract
In this exploratory note we ask the question of what a measure of performance for all tasks is like if we use a weighting of tasks based on a difficulty function. This difficulty function depends on the complexity of the (acceptable) solution for the task (instead of a universal distribution over tasks or an adaptive test). The resulting aggregations and decompositions are (now retrospectively) seen as the natural (and trivial) interactive generalisation of the C-tests.
Cite
@article{arxiv.1412.8529,
title = {A note about the generalisation of the C-tests},
author = {Jose Hernandez-Orallo},
journal= {arXiv preprint arXiv:1412.8529},
year = {2015}
}
Comments
16 pages