Learning $\textit{Ex Nihilo}$

TL;DR

This paper proposes the concept of learning ex nihilo, where agents learn from nothing through formal deductive and inductive reasoning within a cognitive calculus, aiming to bridge logic-based reasoning with machine learning.

Contribution

It introduces the novel concept of ex nihilo learning, formalizes it within a cognitive calculus, and discusses its potential integration with existing machine learning frameworks.

Findings

Defines ex nihilo learning conceptually and formally.

Highlights the challenge and potential for integrating logic-based reasoning with ML.

Encourages interdisciplinary collaboration for future implementation.

Abstract

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.