Program Error Detection/Correction: Turning PAC Learning into PERFECT Learning (Abstract)

Blum, Manuel

doi:10.1007/3-540-63577-7_31

Program Error Detection/Correction: Turning PAC Learning into PERFECT Learning (Abstract)

Manuel Blum

ALT 1997 pp. 1

doi:10.1007/3-540-63577-7_31 /alt/1997/blum1997alt-program/

Abstract

Computational learning theory is concerned with developing “scratch” a probably approximately correct (PAC) algorithm to solve a given computational problem. Program error detection /correction is concerned with transforming programs — such as these — which are correct on most instances into programs that are correct on all instances. The two approaches together enable one to generate a perfect program from scratch. The goal of this talk is to describe how this latter error detection/correction of algorithms works, and to encourage its integration into learning theory.

PDF ALT Semantic Scholar

Cite

Text

Blum. "Program Error Detection/Correction: Turning PAC Learning into PERFECT Learning (Abstract)." International Conference on Algorithmic Learning Theory, 1997. doi:10.1007/3-540-63577-7_31

Markdown

[Blum. "Program Error Detection/Correction: Turning PAC Learning into PERFECT Learning (Abstract)." International Conference on Algorithmic Learning Theory, 1997.](https://mlanthology.org/alt/1997/blum1997alt-program/) doi:10.1007/3-540-63577-7_31

BibTeX

@inproceedings{blum1997alt-program,
  title     = {{Program Error Detection/Correction: Turning PAC Learning into PERFECT Learning (Abstract)}},
  author    = {Blum, Manuel},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {1997},
  pages     = {1},
  doi       = {10.1007/3-540-63577-7_31},
  url       = {https://mlanthology.org/alt/1997/blum1997alt-program/}
}