Experience-grounded semantics: a theory for intelligent systems

Hammer

2018

Front. Robot. AI

Self Cite

This article describes and discusses the self-related mechanisms of a general-purpose intelligent system, NARS. This system is designed to be adaptive and to work with insufficient knowledge and resources. The system's various cognitive functions are uniformly carried out by a central reasoning-learning process following a "non-axiomatic" logic. This logic captures the regularities of human empirical reasoning, where all beliefs are revisable according to evidence, and the meaning of concepts are grounded in the system's experience. NARS perceives its internal environment basically in the same way as how it perceives its external environment although the sensors involved are completely different. Consequently, its self-knowledge is mostly acquired and constructive, while being incomplete and subjective. Similarly, self-control in NARS is realized using mental operations, which supplement and adjust the automatic inference control routine. It is argued that a general-purpose intelligent system needs the notion of a "self," and the related knowledge and functions are developed gradually according to the system's experience. Such a mechanism has been implemented in NARS in a preliminary form.

Section: Experience-grounded Semanticsmentioning

confidence: 99%

“…In the simplest implementation of NARS, its experience is a stream of Narsese sentences, which will be summarized to become the system's beliefs, which is also called the system's knowledge. This semantics is formally defined and fully discussed in the study by Wang (2005Wang ( , 2006.…”

Section: Experience-grounded Semanticsmentioning

confidence: 99%

Self in NARS, an AGI System

Hammer

2018

Front. Robot. AI

Self Cite

“…The details of this "experience-grounded semantics" is explained and discussed in (Wang, 2005;Wang, 2006). Though many people have argued for the importance of experience in intelligence and cognition, no other work has explicitly and formally defined the central semantic notions 'meaning' and 'truth-value' as functions of the system's experience, and specified the details in their computational implementation.…”

Section: Embodiment In Narsmentioning

confidence: 99%

Embodiment: Does a laptop have a body?

Proceedings of the 2nd Conference on Artificial General Intelligence (2009)

2009

Self Cite

This paper analyzes the different understandings of "embodiment". It argues that the issue is not on the hardware a system is implemented in (that is, robot or conventional computer), but on the relation between the system and its working environment. Using an AGI system NARS as an example, the paper shows that the problem of disembodiment can be solved in a symbolic system implemented in a conventional computer, as far as the system makes realistic assumptions about the environment, and adapts to its experience. This paper starts by briefly summarizing the appeal for embodiment, then it analyzes the related concepts, identifies some misconceptions, and suggests a solution, in the context of AGI research.

“…In this way, Narsese gets an experience-grounded semantics (Wang, 2005). According to this semantics, the truth-value of a statement is determined by how much the statement is supported (or refuted) by the evidence collected from the system's experience, rather than by how well the statement corresponds to a fact in the outside world; the meaning of a term is determined by the role the term plays in the system's experience (that is, how it is related to other terms by the inheritance relation and its variants), rather than by an entity in the outside world referred to by the term.…”

Section: Representation Languagementioning

confidence: 99%

“…The confidence factor is a real number in (0, 1), defined as the proportion of current available evidence among future available evidence, after the coming of a unit amount of new evidence, that is, c = w/(w +1). For the current discussion, "evidence" can be understood intuitively, and its formal definition and measurement (such as the above w + and w) have been given in several publications, such as Wang (2005Wang ( , 2006.…”

Section: Representation Languagementioning

confidence: 99%

Analogy in a general-purpose reasoning system

Cognitive Systems Research

2009

Self Cite

This paper introduces the various forms of analogy in NARS, a generalpurpose reasoning system. NARS is an AI system designed to be adaptive and to work with insufficient knowledge and resources. In the system, multiple types of inference, including analogy, deduction, induction, abduction, comparison, and revision, are unified both in syntax and in semantics. The system can also carry out relational and structural analogy, in ways comparable to (though different from) that in some other models of analogy, such as Copycat and SME. The paper addresses several theoretical issues in the study of analogy, including the specification and justification of analogy, the context sensitivity of analogy, as well as the role analogy plays in intelligence and cognition.