A Step from Probabilistic Programming to Cognitive Architectures
Artificial Intelligence
2016-05-05 v1
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.
Cite
@article{arxiv.1605.01180,
title = {A Step from Probabilistic Programming to Cognitive Architectures},
author = {Alexey Potapov},
journal= {arXiv preprint arXiv:1605.01180},
year = {2016}
}
Comments
4 pages