2000 character limit reached
Bridging Generative Networks with the Common Model of Cognition (2403.18827v1)
Published 25 Jan 2024 in cs.AI, cs.LG, cs.NE, and q-bio.NC
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.
- The atomic components of thought. Mahwah, NJ: Lawrence Erlbaum Associates.
- Superposition of many models into one. In Advances in Neural Information Processing Systems 32, 10868–10877. Curran Associates, Inc.
- Clark, A. 2013. Whatever next? Predictive brains, situated agents, and the future of cognitive science. Behavioral and Brain Sciences, 36(3): 181–204.
- Metacognitive threshold: a computational account. In Proceedings of the 21st Annual Conference of the Cognitive Science Society.
- Metacognitive skill: how it is acquired. In Proceedings of the 45th Annual Conference of the Cognitive Science Society, 2880–2887.
- Eliasmith, C. 2013. How to build a brain: A neural architecture for biological cognition. New York, NY: Oxford University Press.
- Does ACT-R Model Me? In Proceedings of the 18th International Conference on Cognitive Modeling, 71–74. University Park, PA: Applied Cognitive Science Lab, Penn State.
- Reasoning with Transformer-based Models: Deep Learning, but Shallow Reasoning. In International Conference on Automated Knowledge Base Construction (AKBC). online, United States.
- Neuro-symbolic approaches in artificial intelligence. National Science Review, 9(6): nwac035.
- The Power of Predictions: An Emerging Paradigm for Psychological Research. Current Directions in Psychological Science, 28(3): 280–291.
- On the link between conscious function and general intelligence in humans and machines. Transactions on Machine Learning Research.
- Holographic Declarative Memory: Distributional Semantics as the Architecture of Memory. Cognitive Science, 44(11): e12904.
- Holographic declarative memory and the fan effect: A test case for a new memory model for ACT-R. In Proceedings of the 13th International Conference on Cognitive Modeling, 148–153. University of Groningen.
- Holographic Declarative Memory: Using distributional semantics within ACT-R. In Laird, J.; Lebiere, C.; and Rosenbloom, P. S., eds., The 2017 AAAI Fall Symposium Series: Technical Reports, 382–387. The AAAI Press.
- An overview of the EPIC architecture for cognition and performance with application to human-computer interaction. Human–Computer Interaction, 12(4): 391–438.
- Laird, J. E. 2012. The Soar Cognitive Architecture. Cambridge, MA: MIT Press.
- A Standard Model of the Mind: Toward a Common Computational Framework Across Artificial Intelligence, Cognitive Science, Neuroscience, and Robotics. AI Magazine, 38(4): 13–26.
- The SAL Integrated Cognitive Architecture. In 2008 AAAI Fall Symposium Series, 98–104.
- Catastrophic Interference in Predictive Neural Network Models of Distributional Semantics. Comput. Brain Behav., 4(1): 18–33.
- Newell, A. 1973. You can’t play 20 questions with nature and win. In Visual information processing, 283–308. New York: Academic Press.
- Newell, A. 1994. Unified theories of cognition. Harvard University Press.
- OpenAI. 2022. Introducing ChatGPT. OpenAI.com.
- Active inference: the free energy principle in mind, brain, and behavior. MIT Press.
- Pearl, J. 2009. Causality. Cambridge university press.
- The Sigma Cognitive Architecture and System: Towards Functionally Elegant Grand Unification. Journal of Artificial General Intelligence, 7(1): 1–103.
- Dynamically structured holographic memory. Biologically Inspired Cognitive Architectures, 9: 9–32.
- The Role of Process in the Rational Analysis of Memory. Cognitive Psychology, 32(3): 219–250.
- Reduction of dopamine in basal ganglia and its effects on syllable sequencing in speech: a computer simulation study. Basal Ganglia, 6(1): 7–17.
- A Command Structure for Complex Information Processing. In Proceedings of the May 6-8, 1958, Western Joint Computer Conference: Contrasts in Computers, IRE-ACM-AIEE ’58 (Western), 119–128. New York, NY, USA: Association for Computing Machinery. ISBN 9781450378642.
- Stewart, T. C. 2007. A methodology for computational cognitive modelling. Ph.D. thesis, Institute of Cognitive Science, Carleton University, Canada.
- Symbolic reasoning in spiking neurons: A model of the cortex/basal ganglia/thalamus loop. In Proceedings of the 32nd Annual Conference of the Cognitive Science Society, 1100–1105. Cognitive Science Society.
- Analysis of the human connectome data supports the notion of a “Common Model of Cognition” for human and human-like intelligence across domains. NeuroImage, 235: 118035.
- Sun, R. 2017. The CLARION cognitive architecture: toward the mind. In Chipman, S., ed., The Oxford Handbook of Cognitive Science, 117–133. Oxford University Press.
- Using GOMS for Modeling Routine Tasks Within Complex Sociotechnical Systems: Connecting Macrocognitive Models to Microcognition. Journal of Cognitive Engineering and Decision Making, 1(2): 186–211.
- Proposal to add emotion to the standard model. In 2017 AAAI Fall Symposium Series, 487–492.