A goal-driven neural propositional interpreter.

P M Lima

doi:10.1142/s012906570100076x

Home/Archive/PubMed

PubMed · 11574968

A goal-driven neural propositional interpreter.

P M Lima

View original source ↗Export metadata ↓

Abstract

This work presents ARQ-PROP-II, the propositional version of a neural engine for finding proofs by refutation using the Resolution Principle. This neural architecture does not require special arrangements or modules to do forward or backward reasoning, being driven by the goal posed to it. ARQ-PROP-II is capable of integrated monotonic reasoning with complete and incomplete knowledge. The neural mechanism presented herein is the first to our knowledge that does not require that the knowledge base be either pre-encoded or learnt.

Explore related subjects

Goals Neural Networks, Computer Journal Article Research Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

P M Lima. 2001. A goal-driven neural propositional interpreter.. https://doi.org/10.1142/s012906570100076x

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2006

Infants' imitation of goal-directed actions: the role of movements and action effects.

This paper reviews studies on infants' imitation of goal-directed actions in the first two years of life. Special emphasis is given to the role of the two observable components of an action, that is, the movement and the action effects, on infants' replication of target actions. The reviewed studies provide evidence that infants benefit most from a full demonstration of both movements and effects. If movements are demonstrated in isolation, infants may encode this information, but they preferentially reproduce actions that lead to salient effects. If action effects are presented in isolation, infants younger than 19 months usually fail to emulate the unseen movements that would be necessary to produce these effects. Infants' ability to predict action effects or to infer unseen movements from incomplete demonstrations improves substantially at the end of the second year of life. It is concluded that the capability to learn relations between movements and action effects by observation, and the knowledge about movement-effect relations acquired so far, may be important factors underlying the developmental changes in infants' imitation of goal-directed actions.

Goals↗

PubMed2006

What do you do for a living? Toward a more succinct definition of health services research.

This commentary discusses the need for, and the advantages of, a more concise, revised definition of the field of health services research. It argues for a definition that includes not only the topics on which health services research focuses but also the goals of health services research. A number of condensed definitions are provided for consideration.

Goals↗

PubMed2006

Do student-defined learning issues increase quality and quantity of individual study?

An experiment was conducted in the context of a problem-based learning course to investigate the influence of a learning-goal-free problem scenario on the quality and quantity of individual study. In half of the tutorial groups, the problem scenario was constructed in such a way that it provided useful learning issues (goal-specified condition), whereas in the other half of the tutorial groups, the problem scenario did not provide learning issues (goal-free condition). It was demonstrated that students in the goal-free condition read more articles, studied longer, and spent more time reporting the studied literature than their peers in the goal-specified condition. These findings suggest that the use of goal-free problems has a positive effect on the students' individual study and the extensiveness of the tutorial group meeting.

Goals↗