arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.03189cs.AI
收藏

涌现因果性与意识的基础

Emergent Causality and the Foundation of Consciousness

The Australian National University(澳大利亚国立大学)

Michael Timothy Bennett

AI总结:

该研究探讨交互场景下通用智能的帕累托最优形式体系中因果干预表示的涌现机制,论证变量作为抽象概念的属性,说明因果干预可通过归纳涌现,进而为意识的相关层面提供机制性解释。

摘要:

为了在交互场景中做出准确推断,智能体不能将对事件的被动观察与主动干预引发事件相混淆。$do$算子将干预形式化,使我们得以推理干预的效果。然而,目前存在一些交互场景下通用智能的帕累托最优数学形式体系,它们在预设无显式干预表示的情况下,仍能做出最大程度准确的推断。我们研究了其中一种形式体系。我们证明,在缺少$do$算子的情况下,干预可以用一个变量来表示。随后我们提出,变量属于抽象概念,而之所以需要提前显式表示干预,仅仅是因为我们预设了这类抽象概念。上述形式体系规避了这一问题,因此在初始条件允许的情况下,相关因果干预的表示会通过归纳过程涌现出来。这些涌现的抽象概念可作为自我以及其他任何对象的表示,只要这些对象的干预会影响目标的达成。我们认为,这解释了个体如何推理自身与他人的身份和意图,以及他人感知到的自身身份意图等问题。从狭义上讲,这描述了觉知的本质,也是对意识相关层面的一种机制性解释。

英文摘要:

To make accurate inferences in an interactive setting, an agent must not confuse passive observation of events with having intervened to cause them. The $do$ operator formalises interventions so that we may reason about their effect. Yet there exist pareto optimal mathematical formalisms of general intelligence in an interactive setting which, presupposing no explicit representation of intervention, make maximally accurate inferences. We examine one such formalism. We show that in the absence of a $do$ operator, an intervention can be represented by a variable. We then argue that variables are abstractions, and that need to explicitly represent interventions in advance arises only because we presuppose these sorts of abstractions. The aforementioned formalism avoids this and so, initial conditions permitting, representations of relevant causal interventions will emerge through induction. These emergent abstractions function as representations of one`s self and of any other object, inasmuch as the interventions of those objects impact the satisfaction of goals. We argue that this explains how one might reason about one`s own identity and intent, those of others, of one`s own as perceived by others and so on. In a narrow sense this describes what it is to be aware, and is a mechanistic explanation of aspects of consciousness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑