Towards a Predictive Processing Implementation of the Common Model of Cognition
This work addresses the problem of developing more scalable and flexible cognitive architectures for AI researchers, though it appears incremental as it builds on existing models without claiming specific performance gains.
The authors tackled the challenge of implementing a cognitive architecture by proposing a system based on neural generative coding and holographic associative memory, aiming to enable continual learning from diverse tasks and model human performance at larger scales than existing architectures.
In this article, we present a cognitive architecture that is built from powerful yet simple neural models. Specifically, we describe an implementation of the common model of cognition grounded in neural generative coding and holographic associative memory. The proposed system creates the groundwork for developing agents that learn continually from diverse tasks as well as model human performance at larger scales than what is possible with existant cognitive architectures.