Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Bridging Generative Networks with the Common Model of Cognition

Robert L. West, Spencer Eckler, Brendan Conway-Smith, Nico Turcas, Eilene Tomkins-Flanagan, Mary Alexandria Kelly

Abstract

This article presents a theoretical framework for adapting the Common Model of Cognition to large generative network models within the field of artificial intelligence. This can be accomplished by restructuring modules within the Common Model into shadow production systems that are peripheral to a central production system, which handles higher-level reasoning based on the shadow productions' output. Implementing this novel structure within the Common Model allows for a seamless connection between cognitive architectures and generative neural networks.

Bridging Generative Networks with the Common Model of Cognition

Abstract

This article presents a theoretical framework for adapting the Common Model of Cognition to large generative network models within the field of artificial intelligence. This can be accomplished by restructuring modules within the Common Model into shadow production systems that are peripheral to a central production system, which handles higher-level reasoning based on the shadow productions' output. Implementing this novel structure within the Common Model allows for a seamless connection between cognitive architectures and generative neural networks.
Paper Structure (11 sections, 4 figures, 1 table)

This paper contains 11 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Components of the Common Model
  3. Chunks
  4. Buffers
  5. Modules and Declarative Memory
  6. Production Rules
  7. Shadow Productions
  8. Newell’s Levels
  9. Proposed Framework
  10. Conclusions
  11. Acknowledgments

Figures (4)

  • Figure 1: The Common Model Architecture.
  • Figure 2: The Pipeline Architecture. Modules in the CMC connect to underlying networks associated with their functionality.
  • Figure 3: The Middle Memory Architecture. Generative network outputs are tagged with the network that produced them and deposited into the interface (Middle Memory) where they can be accessed by the shadow productions.
  • Figure 4: Context and Attention. This depicts how context and attention can feed into the generative networks.