Neural-Net Implementation of Complex Symbol-Processing in a Mental Model Approach to Syllogistic Reasoning
Abstract
A neural net system called is described. Conposit performs rule-based manipulation of very short term, complex symbolic data structures. This paper concentrates on a simulated version of Conposit that embodies core aspects of Johnson-Laird's mental model theory of syllogistic reasoning. This Conposit version is not intended to be a psychological theory, but rather to act as a test and demonstration of the power and flexibility of Conposit's unusual connectionist techniques for encoding the structure of data.
Cite
Text
Barnden. "Neural-Net Implementation of Complex Symbol-Processing in a Mental Model Approach to Syllogistic Reasoning." International Joint Conference on Artificial Intelligence, 1989.Markdown
[Barnden. "Neural-Net Implementation of Complex Symbol-Processing in a Mental Model Approach to Syllogistic Reasoning." International Joint Conference on Artificial Intelligence, 1989.](https://mlanthology.org/ijcai/1989/barnden1989ijcai-neural/)BibTeX
@inproceedings{barnden1989ijcai-neural,
title = {{Neural-Net Implementation of Complex Symbol-Processing in a Mental Model Approach to Syllogistic Reasoning}},
author = {Barnden, John A.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1989},
pages = {568-573},
url = {https://mlanthology.org/ijcai/1989/barnden1989ijcai-neural/}
}