Inductive Inference Theory - A Unified Approach to Problems in Pattern Recognition and Artificial Intelligence
Abstract
Recent results in induction theory are reviewed that demonstrate the general adequacy of the induction system of Solomonoff and Willis. Several problems in pattern recognition and A.I. are investigated through these methods. The theory is used to obtain the a priori probabilities that are necessary in the application of stochastic languages to pattern recognition. A simple, quantitative solution is presented for part of Winston’s problem of learning structural descriptions from examples. In contrast to work in non-probabilistic prediction, the present methods give probability values that can be used with decision theory to make critical decisions.
Cite
Text
Solomonott. "Inductive Inference Theory - A Unified Approach to Problems in Pattern Recognition and Artificial Intelligence." International Joint Conference on Artificial Intelligence, 1975.Markdown
[Solomonott. "Inductive Inference Theory - A Unified Approach to Problems in Pattern Recognition and Artificial Intelligence." International Joint Conference on Artificial Intelligence, 1975.](https://mlanthology.org/ijcai/1975/solomonott1975ijcai-inductive/)BibTeX
@inproceedings{solomonott1975ijcai-inductive,
title = {{Inductive Inference Theory - A Unified Approach to Problems in Pattern Recognition and Artificial Intelligence}},
author = {Solomonott, R.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1975},
pages = {274-280},
url = {https://mlanthology.org/ijcai/1975/solomonott1975ijcai-inductive/}
}