The knowledge level in cognitive architectures: Current limitations and possible developments

@article{Lieto2018TheKL,
  title={The knowledge level in cognitive architectures: Current limitations and possible developments},
  author={Antonio Lieto and Christian Lebiere and Alessandro Oltramari},
  journal={Cognitive Systems Research},
  year={2018},
  volume={48},
  pages={39-55}
}

Tables from this paper

Representational Limits in Cognitive Architectures
TLDR
The possibility of integrating external, but architecturally compliant, cognitive systems into the knowledge representation and processing mechanisms of the CAs is discussed.
Towards a unifying framework for conceptual represention and reasoning in cognitive systems
TLDR
The additional integrations presented here suggest that the underlying knowledge representation and reasoning structure adopted in DUAL-PECCS can be used as a unifying framework for the knowledge level of agents endowed with different cognitive architectures.
Representational Issues in the Debate on the Standard Model of the Mind
TLDR
This paper focuses on the representational models concerning the Declarative Memories of current Cognitive Architectures and suggests that the Conceptual Spaces, a representational framework developed by Gardenfors, is worth-considering to address such problems.
Representation of Concepts in AI: Towards a Teleological Explanation
TLDR
A teleological explanation of the most widely shared approaches in AI to the representation of concepts and an illustration of how the proposed explanation could constitute a contribution in the context of explainable AI.
What Cognitive Research Can Do for AI: a Case Study (short paper)
TLDR
Evidence of a renewed collaboration between AI and CogSci research agendas is provided by showing a recent case study on a commonsense reasoning system, built by using insights from cognitive semantics.
A Goal-Oriented Framework for Knowledge Invention and Creative Problem Solving in Cognitive Architectures
TLDR
A reasoning framework for knowledge invention and creative problem solving that can integrate and extend the knowledge level mechanism of diverse cognitive architectures (CAs) and is compliant with the general tenets of the Standard Model of Mind.
Content-Centric Computational Cognitive Modeling
That human-level cognitive systems will require a lot of knowledge is common knowledge. However, for a number of reasons, issues of content are not directly addressed at scale by the cognitive
Cognitive Architectures on Discourse
  • M. Iza
  • Computer Science
    Living Machines
  • 2018
TLDR
The use of cognitive architectures are discussed in order to solve the problems that arise from rigid models based on AI.
Knowledge acquisition through introspection in Human-Robot Cooperation
...
...

References

SHOWING 1-10 OF 79 REFERENCES
Symbolic, Conceptual and Subconceptual Representations
TLDR
This work aims at understanding how information is represented and processed in different kinds of agents, biological as well as artificial, at the level of humans and other animals.
Endowing a Cognitive Architecture with World Knowledge
TLDR
The Wikipedia knowledge base is used to derive a declarative database for the ACT-R cognitive architecture, complete both with tens of millions of world-knowledge facts and with estimates of the accessibility (activation) of these facts.
A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents
TLDR
A broad survey of the various paradigms of cognition, addressing cognitivist (physical symbol systems) approaches, emergent systems approaches, encompassing connectionist, dynamical, and enactive systems, and also efforts to combine the two in hybrid systems.
Cognitive architectures: Research issues and challenges
Pursuing Artificial General Intelligence by Leveraging the Knowledge Capabilities of ACT-R
TLDR
This paper describes an artificial system that benefits from both mechanism---centered and knowledge---centered approaches, and integrates the ACT-R cognitive architecture with SCONE, a knowledge-based system for ontological reasoning, to combineACT-R's subsymbolic cognitive mechanisms withSCONE's knowledge representation and inference capabilities.
Cognitive Architectures and Autonomy: A Comparative Review
TLDR
This paper reviews selected systems and architectures built expressly to address integrated skills and highlights principles and features of these systems that seem promising for creating generally intelligent systems with some level of autonomy.
Representing Concepts in Formal Ontologies: Compositionality vs. Typicality Effects"
TLDR
This paper outlines some proposals for concept representation in formal ontologies, which take into account suggestions from psychological research, and makes the basic assumption that knowledge representation systems whose design takes into account evidence from experimental psychology may therefore give better results in many applications.
Dual PECCS: a cognitive system for conceptual representation and categorization
TLDR
An advanced version of Dual-PECCS, a cognitively-inspired knowledge representation and reasoning system aimed at extending the capabilities of artificial systems in conceptual categorization tasks, is presented and integrated and tested into two cognitive architectures, ACT-R and CLARION, implementing different assumptions on the underlying invariant structures governing human cognition.
...
...