40 years of cognitive architectures: core cognitive abilities and practical applications

@article{Kotseruba201840YO,
  title={40 years of cognitive architectures: core cognitive abilities and practical applications},
  author={Iuliia Kotseruba and John K. Tsotsos},
  journal={Artificial Intelligence Review},
  year={2018},
  volume={53},
  pages={17-94}
}
In this paper we present a broad overview of the last 40 years of research on cognitive architectures. [] Key Method We use various visualization techniques to highlight the overall trends in the development of the field. In addition to summarizing the current state-of-the-art in the cognitive architecture research, this survey describes a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need…
A Study in Activation: Towards a Common Lexicon and Functional Taxonomy in Cognitive Architectures
TLDR
A lexicon ofactivation-related concepts and a functional taxonomy that enumerates many activation-related “design patterns” that have appeared in cognitive architectures, which includes one of the most varied and comprehensive adoptions of activation- related functionality.
CogNGen: Constructing the Kernel of a Hyperdimensional Predictive Processing Cognitive Architecture
TLDR
A new cognitive architecture that combines two neurobiologically plausible, computational models: a variant of predictive processing known as neural generative coding (NGC) and hyperdimensional / vector-symbolic models of human memory, which is tested on a set of maze-learning tasks.
Natural Computational Architectures for Cognitive Info-Communication
TLDR
A set of perspectives and approaches which have shaped theDevelopment of biologically inspired computational models in the recent past that can lead to the development of biologically more realistic cognitive architectures are presented.
Cognitive Machinery and Behaviours
TLDR
The proposed model IPSEL for Information Processing System with Emerging Logic is a functional model of information processing systems inspired by several established theories, including deep reinforcement learning mechanisms and grounded cognition theories from artificial intelligence research, and dual-process theory from psychology.
Attention: The Messy Reality
TLDR
A hierarchy of dynamically defined closed-loop control processes is proposed, each with its own optimization objective, which is extensible to multiple layers and although mostly speculative, simulation and experimental work support important components.
A Common Architecture for Human and Artificial Cognition Explains Brain Activity Across Domains
TLDR
It is suggested that a common, functional computational blueprint for human-like intelligence also captures the neural architecture that underpins human cognition, and best explains human neuroimaging activity across cognitive domains.
Conceptual Design of the Memory System of the Robot Cognitive Architecture ArmarX
TLDR
This work described conceptual and technical characteristics such a memory system of a humanoid robot performing tasks in human-centered environments should support, together with the underlying data representation, and extended the robot software framework ArmarX into a cognitive architecture that is used in robots of the ARMAR humanoid robot family.
Modeling Human Behavior Part II - Cognitive approaches and Uncertainty
As we discussed in Part I of this topic [30], there is a clear desire to model and comprehend human behavior. Given the popular presupposition of human reasoning as the standard for learning and
Demanding and Designing Aligned Cognitive Architectures
TLDR
This work identifies several technically tractable but currently unfashionable options for improving AI alignment and considers how current fashions in machine learning create a narrative pull that participants in technical and policy discussions should be aware of, so they can compensate for it.
...
...

References

SHOWING 1-10 OF 675 REFERENCES
The Leabra Cognitive Architecture: How to Play 20 Principles with Nature and Win!
This chapter provides a synthetic review of a long-term effort to produce an internally consistent theory of the neural basis of human cognition, the Leabra cognitive architecture, which explains a
Attention and Cognition: Principles to Guide Modeling
TLDR
A set of elements that may be considered as the components of attention, without any claims or completeness or optimality, and these will act as the first level set of constraints on any modeling activity are proposed.
Précis of Unified theories of cognition
  • A. Newell
  • Psychology
    Behavioral and Brain Sciences
  • 1992
TLDR
The book presents the case that cognitive science should turn its attention to developing theories of human cognition that cover the full range of human perceptual, cognitive, and action phenomena by presenting an exemplar unified theory of cognition, SOAR, which is realized as a software system.
Strategic Cognitive Sequencing: A Computational Cognitive Neuroscience Approach
We address strategic cognitive sequencing, the “outer loop” of human cognition: how the brain decides what cognitive process to apply at a given moment to solve complex, multistep cognitive tasks. We
Brief Survey of Cognitive Architectures
TLDR
This chapter gives a rough high-level overview of the various AGI architectures at play in the field today and has a bias toward other work with some direct relevance to CogPrime, but not an overwhelming bias.
The Newell Test for a theory of cognition
TLDR
12 criteria that the human cognitive architecture would have to satisfy in order to be functional are distilled into 12 criteria: flexible behavior, real-time performance, adaptive behavior, vast knowledge base, dynamic behavior, knowledge integration, natural language, learning, development, evolution, and brain realization.
Memory systems within a cognitive architecture
  • R. Sun
  • Psychology, Computer Science
  • 2012
The importance of cognitive architectures: an analysis based on CLARION
  • R. Sun
  • Computer Science
    J. Exp. Theor. Artif. Intell.
  • 2007
TLDR
In this paper, discussions of issues and challenges in developing cognitive architectures will be undertaken, and an example cognitive architecture (CLARION) will be described.
...
...