A Step from Probabilistic Programming to Cognitive Architectures

TL;DR

This paper explores integrating probabilistic programming with cognitive architectures, proposing implicit generative models and emphasizing declarative knowledge for improved inference capabilities.

Contribution

It introduces a novel approach to represent cognitive architecture components within probabilistic programming, highlighting implicit model specification and declarative knowledge use.

Findings

Implicit specification of generative models is effective.

Declarative knowledge enhances inference efficiency.

Framework unifies probabilistic programming with cognitive architectures.

Abstract

Probabilistic programming is considered as a framework, in which basic components of cognitive architectures can be represented in unified and elegant fashion. At the same time, necessity of adopting some component of cognitive architectures for extending capabilities of probabilistic programming languages is pointed out. In particular, implicit specification of generative models via declaration of concepts and links between them is proposed, and usefulness of declarative knowledge for achieving efficient inference is briefly discussed.