arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1903.03515cs.AI
收藏

学习$\textit{Ex Nihilo}$

Learning $\textit{Ex Nihilo}$

Rensselaer Polytechnic Institute (RPI)(伦斯勒理工学院(RPI))

Selmer Bringsjord, Naveen Sundar Govindarajulu

摘要:

本文介绍,理论上和某种程度上正式,新的概念,学习$\textit{ex nihilo}$,意图(显然)是类似的概念,创造$\textit{ex nihilo}$。学习$\textit{ex nihilo}$是一个代理的学习“从无到有”,通过适当的就业模式的演绎和归纳推理。该推理必须与$\textit{cognitive calculus}$中的形式证明/论证理论(即,粗略地说,内涵高阶多算子量化逻辑),并且在某些先验知识以及某些先验和当前兴趣的上下文中,将该推理应用于由代理接收的感知。学习$\textit{ex nihilo}$对当代形式的ML来说是一个挑战,确实是一个严峻的挑战,但挑战是在寻求刺激尝试的精神中提供的,在非逻辑主义ML研究人员和工程师的一部分,与那些拥有学习$\textit{ex nihilo}$框架的人合作,并最终尝试在实现层面直接与这些框架集成。除其他外,这种集成将需要最先进的自动推理机和高表现力规划器与统计/连接主义ML技术的共生互操作。

英文摘要:

This paper introduces, philosophically and to a degree formally, the novel concept of learning $\textit{ex nihilo}$, intended (obviously) to be analogous to the concept of creation $\textit{ex nihilo}$. Learning $\textit{ex nihilo}$ is an agent's learning "from nothing," by the suitable employment of schemata for deductive and inductive reasoning. This reasoning must be in machine-verifiable accord with a formal proof/argument theory in a $\textit{cognitive calculus}$ (i.e., roughly, an intensional higher-order multi-operator quantified logic), and this reasoning is applied to percepts received by the agent, in the context of both some prior knowledge, and some prior and current interests. Learning $\textit{ex nihilo}$ is a challenge to contemporary forms of ML, indeed a severe one, but the challenge is offered in the spirt of seeking to stimulate attempts, on the part of non-logicist ML researchers and engineers, to collaborate with those in possession of learning-$\textit{ex nihilo}$ frameworks, and eventually attempts to integrate directly with such frameworks at the implementation level. Such integration will require, among other things, the symbiotic interoperation of state-of-the-art automated reasoners and high-expressivity planners, with statistical/connectionist ML technology.

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。

↑