Scruff: A Deep Probabilistic Cognitive Architecture for Predictive Processing

Pfeffer, A. and Lynn, S.

Biologically Inspired Cognitive Architectures 2018

The theory of predictive processing encompasses several elements that make it attractive as the underlying computational approach for a cognitive architecture. We introduce a new cognitive architecture, Scruff, capable of implementing predictive processing models by incorporating key properties of neural networks into the Bayesian probabilistic programming framework. We illustrate the Scruff approach with conditional linear Gaussian (CLG) models, noisy-or models, and a Bayesian variation of the Rao-Ballard linear algebra model of predictive vision.

For More Information

To learn more, contact Avi Pfeffer.

(Please include your name, address, organization, and the paper reference. Requests without this information will not be honored.)