Structural representation and reasoning in a hybrid cognitive architecture

@article{Licato2014StructuralRA,
  title={Structural representation and reasoning in a hybrid cognitive architecture},
  author={John Licato and Ron Sun and Selmer Bringsjord},
  journal={2014 International Joint Conference on Neural Networks (IJCNN)},
  year={2014},
  pages={891-898}
}
Psychologically and neurobiologically plausible models of knowledge often must make a difficult choice between distributed and localist representation. Distributed representation can be flexible and hold up well to noisy data, but localist models allow for structured knowledge to be represented unambiguously and reasoned over in rigorous, transparent fashion. We present a way of representing knowledge within the hybrid cognitive architecture CLARION. Our system allows both structured knowledge… 
View on IEEE
kryten.mm.rpi.edu
12 Citations
Background Citations
5
Methods Citations
3

Figures from this paper

12 Citations

Using Meta-Cognition for Regulating Explanatory Quality Through a Cognitive Architecture

TLDR
This work tackles both the explicit and implicit effects of this cognitive feature and incorporates them into a comprehensive cognitive architecture: CLARION (especially its meta-cognitive and non-action-centered subsystems).

Re-framing the characteristics of concepts and their relation to learning and cognition in artificial agents

Contemporary cognitive architectures: a comparative study of structures and adaptability

Cognitive architectures aim to provide blueprints for achieving artificial general intelligence AGI. Cognitive models that can provide crucial clues to the working of human mind are typically built…

Modeling the Creation and Development of Cause-Effect Pairs for Explanation Generation in a Cognitive Architecture

TLDR
This paper discusses the development of causal representations in children, by analyzing the literature surrounding a Piagetian experiment, and shows how the conditions making cause-effect pair creation possible can start to be modeled using a combination of feature-extraction techniques and structured knowledge representation in the hybrid cognitive architecture CLARION.

How Can We Reduce the Gulf between Artificial and Natural Intelligence?

TLDR
A very long-term multi-disciplinary research programme addressing inadequacies in current AI, cognitive science, robotics, psychology, neuroscience, philosophy of mathematics and philosophy of mind.

Using a Hybrid Cognitive Architecture to Model Children's Errors in an Analogy Task

TLDR
This modeling is done using the hybrid cognitive architecture CLARION, and a method of representing structured knowledge within CLAR- ION’s dual-process system, to model the performance of children on the Goswami and Brown (1990) analogy task, paying close attention to the distribution of errors children made on the task.

The Case for Explicit Ethical Agents

TLDR
It will be the job of agent designers to ensure that autonomous artificial agents are equipped with the moral and ethical competence to negotiate human societies in order to prevent harm they could cause otherwise by being oblivious to ethics and morality.

KMARF: A Framework for Knowledge Management and Automated Reasoning

TLDR
A generic framework for knowledge management and automated reasoning (KMARF) as an enabler for intelligent adaptive systems that targets multiple reasoning problem classes that can share the same underlying system state representation.

Dynamic representations : building knowledge through an active representational process based on deep generative models

TLDR
The final author version and the galley proof are versions of the publication after peer review and the final published version features the final layout of the paper including the volume, issue and page numbers.

A Framework for Knowledge Management and Automated Reasoning Applied on Intelligent Transport Systems

Cyber-Physical Systems in general, and Intelligent Transport Systems (ITS) in particular use heterogeneous data sources combined with problem solving expertise in order to make critical decisions t…

References

SHOWING 1-10 OF 30 REFERENCES

Relational Reasoning in a Neurally Plausible Cognitive Architecture

TLDR
The LISA model of analogical reasoning represents both relations and objects as patterns of activation distributed over semantic units, integrating these representations into propositional structures using synchrony of firing to provide an a priori account of the limitations of human working memory.

Accounting for Similarity-Based Reasoning within a Cognitive Architecture

TLDR
The paper implements this analysis in a cognitive architecture Clarion, which has previously succeeded in capturing a variety of human learning data in simulations, and demonstrates the significant role played by similarity-based reasoning.

Accounting for a variety of reasoning data within a cognitive architecture

  • R. SunXi Zhang
  • Computer Science, Psychology
    J. Exp. Theor. Artif. Intell.
  • 2006
TLDR
The exploration of both similarity-based reasoning and intuition in this cognitive architecture leads toward a more comprehensive framework of human everyday reasoning.

Connectionist Models of Rule-Based ReasoningRon

TLDR
This work shows that connectionist models of reasoning are not just ``implementations" of their symbolic counterparts, but better computational models of commonsense reasoning.

From Simple Associations to Systemic Reasoning: A Connectionist Representation of Rules, Variables and Dynamic Bindings

TLDR
It is described how a connectionist system made up of simple and slow neuron-like elements can encode millions of facts and rules involving n-ary predicates and variables, and yet perform a variety of inferences within hundreds of milliseconds.

Robust Reasoning: Integrating Rule-Based and Similarity-Based Reasoning

  • R. Sun
  • Computer Science
    Artif. Intell.
  • 1995

A Connectionist Computational Model for Epistemic and Temporal Reasoning

TLDR
This article shows that nonclassical logics, in particular propositional temporal logic and combinations of temporal and epistemic reasoning, can be effectively computed by artificial neural networks.

Compositionality and Biologically Plausible Models

TLDR
The breadth of this handbook demonstrates the diversity of approaches to compositionality that characterize current research, as well as providing detailed discussions of the problems faced by any theory purporting to describe how such systems can occur in the physical brain.

The Cambridge Handbook of Computational Psychology: Declarative/Logic-Based Cognitive Modeling

TLDR
This chapter provides an overview of the book on Introduction to Computational Cognitive Modeling and explores a range of issues associated with computational cognitive modeling and cognitive architectures.

Dual-processing accounts of reasoning, judgment, and social cognition.

TLDR
This article reviews a diverse set of proposals for dual processing in higher cognition within largely disconnected literatures in cognitive and social psychology and suggests that while some dual-process theories are concerned with parallel competing processes involving explicit and implicit knowledge systems, others are concerns with the influence of preconscious processes that contextualize and shape deliberative reasoning and decision-making.