Induction in an Abstraction Space: A Form of Constructive Induction

Drastal, George; Czako, Gabor; Raatz, Stan

Induction in an Abstraction Space: A Form of Constructive Induction

Download BibTeX Cite

Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Machine Learning. Pages 708-711.

Abstract

We report on a learning system MIRO which performs supervised concept formation in an abstraction space. Given a domain theory , the method constructs this abstraction space by deduction over instances, and then performs induction in it rather ~han the initial space defined by instances alone. It is also possible to regard MIRO as a variant of constructive induction. The Vapnik-Chervonenkis model suggests that learning in an abstraction space can result in a substantial speedup, and we provide empirical studies which validate this proposition. We also show that learning in an abstraction space can reciuce the number of false negative and false postive classifications because coincidental patterns are filtered by the deduction process. The method is able to extend an incomplete domain theory represented as attribute-value pairs with a set of rules that represent a disjunctive concept derived from a batch of training instances.

George Drastal, Gabor Czako, and Stan Raatz. 1989. Induction in an Abstraction Space: A Form of Constructive Induction. In Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, IJCAI-89. IJCAI, 708–711. https://ijcai.org/proceedings/1989/113

@inproceedings{ijcai1989p113,
  title     = {Induction in an Abstraction Space: A Form of Constructive Induction},
  author    = {Drastal, George and Czako, Gabor and Raatz, Stan},
  booktitle = {Proceedings of the Eleventh International Joint Conference on
               Artificial Intelligence, {IJCAI-89}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {N. S. Sridharan},
  pages     = {708--711},
  year      = {1989},
  month     = {8},
  note      = {Machine Learning},
  url       = {https://ijcai.org/proceedings/1989/113},
}

TY  - CPAPER
TI  - Induction in an Abstraction Space: A Form of Constructive Induction
AU  - Drastal, George
AU  - Czako, Gabor
AU  - Raatz, Stan
T2  - Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, IJCAI-89
PB  - International Joint Conferences on Artificial Intelligence
PY  - 1989
SP  - 708
EP  - 711
UR  - https://ijcai.org/proceedings/1989/113
ER  -