A Step from Probabilistic Programming to Cognitive Architectures
This work addresses the integration of probabilistic programming and cognitive architectures, potentially benefiting researchers in AI and cognitive science, but it appears incremental as it builds on existing frameworks without introducing a new paradigm.
The paper proposes using probabilistic programming to represent cognitive architecture components in a unified way, and suggests that incorporating cognitive architecture elements can extend the capabilities of probabilistic programming languages, with a focus on implicit generative models and declarative knowledge for efficient inference.
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.