Transformations That Preserve Learnability
Abstract
We consider transformations (performed by general recursive operators) mapping recursive functions into recursive functions. These transformations can be considered as mapping sets of recursive functions into sets of recursive functions. A transformation is said to be preserving the identification type I , if the transformation always maps I -identifiable sets into I -identifiable sets. There are transformations preserving FIN but not EX, and there are transformations preserving EX but not FIN. However, transformations preserving EX_i always preserve EX_j for j < i .
Cite
Text
Ambainis and Freivalds. "Transformations That Preserve Learnability." International Conference on Algorithmic Learning Theory, 1996. doi:10.1007/3-540-61863-5_54Markdown
[Ambainis and Freivalds. "Transformations That Preserve Learnability." International Conference on Algorithmic Learning Theory, 1996.](https://mlanthology.org/alt/1996/ambainis1996alt-transformations/) doi:10.1007/3-540-61863-5_54BibTeX
@inproceedings{ambainis1996alt-transformations,
title = {{Transformations That Preserve Learnability}},
author = {Ambainis, Andris and Freivalds, Rusins},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {1996},
pages = {299-311},
doi = {10.1007/3-540-61863-5_54},
url = {https://mlanthology.org/alt/1996/ambainis1996alt-transformations/}
}