Conjecturing the Cognitive Plausibility of an ANN Theorem-Prover

Authors:
Iara Moema Oberg Vilela;Priscila Machado Vieira Lima
Affiliations:
-;-
Venue:
IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Year:
2001

Citing 5
Cited 0

Higher-order Boltzmann machines

AIP Conference Proceedings 151 on Neural Networks for Computing
Inductive logic programming

New Generation Computing - Selected papers from the international workshop on algorithmic learning theory,1990
Reasoning, nonmonotonicity and learning in connectionist networks that capture propositional knowledge

Artificial Intelligence
An Integrated Approach of Visual Computational Modelling

SBRN '00 Proceedings of the VI Brazilian Symposium on Neural Networks (SBRN'00)
A Neural Propositional Reasoner that is Goal-Driven and Works without Pre-Compiled Knowledge

SBRN '00 Proceedings of the VI Brazilian Symposium on Neural Networks (SBRN'00)

Quantified Score

Hi-index	0.01

Visualization

Abstract

Many models in Artificial Neural Networks Systems seek inspiration from cognitive and biological mechanisms. Taking the opposite direction, this work conjectures on the cognitive plausibility of a propositional version of neural engine that finds proof by refutation using the Resolution Principle. We construct a parallel between the main characteristics of the computional system and several aspects of theories found in the psychology and neurocognitive literature. This way, the identification of an artificial neural explainer, already hypothesized by psychological and neurocognitive works, is of fundamental contribution to the development of the field of artificial cognition.