Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence

TL;DR

This paper introduces a probabilistic formalism called QUERY, inspired by Turing's ideas, to model common-sense reasoning as probabilistic inference through conditional simulation, aiming to replicate human-like flexibility in AI.

Contribution

It presents a novel formalism, QUERY, that formalizes common-sense reasoning as probabilistic inference, synthesizing ideas from AI, cognitive science, and Turing's foundational insights.

Findings

QUERY captures probabilistic conditioning via conditional simulation

Demonstrates how common-sense reasoning can be modeled as probabilistic inference

Unifies concepts from AI, cognitive science, and Turing's work

Abstract

The problem of replicating the flexibility of human common-sense reasoning has captured the imagination of computer scientists since the early days of Alan Turing's foundational work on computation and the philosophy of artificial intelligence. In the intervening years, the idea of cognition as computation has emerged as a fundamental tenet of Artificial Intelligence (AI) and cognitive science. But what kind of computation is cognition? We describe a computational formalism centered around a probabilistic Turing machine called QUERY, which captures the operation of probabilistic conditioning via conditional simulation. Through several examples and analyses, we demonstrate how the QUERY abstraction can be used to cast common-sense reasoning as probabilistic inference in a statistical model of our observations and the uncertain structure of the world that generated that experience. This formulation is a recent synthesis of several research programs in AI and cognitive science, but it also represents a surprising convergence of several of Turing's pioneering insights in AI, the foundations of computation, and statistics.