Рейтинг:  5 / 5

Звезда активнаЗвезда активнаЗвезда активнаЗвезда активнаЗвезда активна

Wang, PeiNARS (Non-Axiomatic Reasoning System), a general-purpose intelligent system, or a "thinking machine", that follows the same principles as the human mind, and can solve problems in various domains, has been developed by Dr. Pei Wang (Department of Computer and Information SciencesCollege of Science & Technology at the Temple University, Philadelphia, Pennsylvania, USA).
Pei Wang homepage | Email: Этот адрес электронной почты защищён от спам-ботов. У вас должен быть включен JavaScript для просмотра. | NARS Projectagi

Когнитивная архитектура NARS разрабатывается исследовательской группой по проекту в Отделении вычислительной техники и информатики (Department of Computer and Information Sciences) Темпльского университета (Temple University) в г. Филадельфия, Пенсильвания, США. Руководит разработкой Пэй Ван (Pei Wang). Материалы разработки представляются ежегодно на конференциях по AGI.

Artificial General Intelligence (AGI): introduction, journal, society, education, lecture notes.

Общие сведения

- Pei Wang is Designer of Non-Axiomatic Reasoning System (NARS), a general-purpose intelligent system that adapts to its environment and works with insufficient knowledge and resources:
introduction, project website, open-source version, discussion group, NARS hybrid architecture.
- NARS - AI Project
- Implemented several versions of the system, and published many papers and a recent book, titled Rigid Flexibility: The Logic of Intelligence (2006).
- A Logical Model of Intelligence — an introduction to NARS:
[The video of a lecture based on this note is on-line: Part 1, 2, 3.]

Pei Wang. Toward a Unified Artificial Intelligence. Published in 2004.
To integrate existing AI techniques into a consistent system, an intelligent core is needed, which is general and flexible, and can use the other techniques as tools to solve concrete problems. Such a system, NARS, is introduced. It is a general-purpose reasoning system developed to be adaptive and capable of working with insufficient knowledge and resources. Compared to traditional reasoning system, NARS is different in all major components (language, semantics, inference rules, memory structure, and control mechanism)."


NARS [From NARS to a Thinking Machine; Rigid Flexibility: The Logic of Intelligence]

What makes NARS different from conventional reasoning systems is its ability to learn from its experience and to work with insufficient knowledge and resources. NARS attempts to uniformly explain and reproduce many cognitive facilities, including reasoning, learning, planning, etc, so as to provide a unified theory, model, and system for AI as a whole. The ultimate goal of this research is to build a thinking machine.

The development of NARS takes an incremental approach consisting four major stages. At each stage, the logic is extended to give the system a more expressive language, a richer semantics, and a larger set of inference rules; the memory and control mechanism are then adjusted accordingly to support the new logic.

In NARS the notion of "reasoning" is extended to represent a system's ability to predict the future according to the past, and to satisfy the unlimited resources demands using the limited resources supply, by flexibly combining justifiable micro steps into macro behaviors in a domain-independent manner.

Pei WANG, Ben GOERTZEL Introduction: Aspects of Artificial General Intelligence
Pei Wang. Artificial General Intelligence" (AGI) — A gentle introduction

Open NARS Software - Downloads. A complete implementation of NAL-1 to NAL-6.

Internet Groups and Mailing Lists:
 Technical discussion on the open-nars project, an intelligent reasoning system.
Project website: http://code.google.com/p/open-nars/

Пэй Ван (Pei Wang) - Информация и публикации

Pei Wang
. A Logical Model of Intelligence — An introduction to NARS

What should AGI Learn from AI and CogSci?
AGI should avoid repeating the same mistakes made by CogSci and AI.

Inference Control in NARS
How inference processes are controlled in NARS, and how to use the mechanism.

Issues in Temporal and Causal Inference
Causal inference can be realized without a predefi.ned causal relation

Natural Language Processing by Reasoning and Learning (extended version)
Some preliminary ideas and results of natural language processing in NARS

Pei Wang. Three fundamental misconceptions of Artificial Intelligence.