Inductive Learning from Good Examples

Ling, Charles X.

Inductive Learning from Good Examples

Download BibTeX Cite

Proceedings of the Twelfth International Joint Conference on Artificial Intelligence. Learning Be Knowledge Acquisition. Pages 751-755.

Abstract

We study what kind of data may ease the computational complexity of learning of Horn clause theories (in Gold's paradigm) and Boolean functions (in PAC-learning paradigm). We give several definitions of good data (basic and generative representative sets), and develop data-driven algorithms that learn faster from good examples, and degenerate to learn in the limit from the ''worst" possible examples. We show that Horn clause theories, kterm DNF and general DNF Boolean functions are polynomially learnable from generative representative presentations.

Charles X. Ling. 1991. Inductive Learning from Good Examples. In Proceedings of the Twelfth International Joint Conference on Artificial Intelligence, IJCAI-91. IJCAI, 751–755. https://ijcai.org/proceedings/1991/110

@inproceedings{ijcai1991p110,
  title     = {Inductive Learning from Good Examples},
  author    = {Ling, Charles X.},
  booktitle = {Proceedings of the Twelfth International Joint Conference on
               Artificial Intelligence, {IJCAI-91}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {John Mylopoulos and Ray Reiter},
  pages     = {751--755},
  year      = {1991},
  month     = {8},
  note      = {Learning Be Knowledge Acquisition},
  url       = {https://ijcai.org/proceedings/1991/110},
}

TY  - CPAPER
TI  - Inductive Learning from Good Examples
AU  - Ling, Charles X.
T2  - Proceedings of the Twelfth International Joint Conference on Artificial Intelligence, IJCAI-91
PB  - International Joint Conferences on Artificial Intelligence
PY  - 1991
SP  - 751
EP  - 755
UR  - https://ijcai.org/proceedings/1991/110
ER  -