Algorithmic knowledge profiles for introspective monitoring in artificial cognitive agents

Piñeres, Manuel Fernando Caro; Gomez, Adan A.; Giraldo, Juan Carlos Pacheco

doi:10.1109/icci-cc.2017.8109792

Cited by 5 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finding errors in reasoning at the object level is the primary aim so that the intelligent system, through sufficient information, can make effective corrective decisions at the meta-level. However, it seems that despite the efforts to integrate introspective operations into the systems, they do not have a model of the knowledge they possess (Caro, Gomez, & Giraldo, 2017).…”

Section: Artificial Intelligence Approaches Aspects Of Metacognitionmentioning

confidence: 99%

“…In the first metacognitive ability, the intelligent agent has a reasoning model for its environment allowing problem-solving. While the second concerns a level of representation of the agent's reasoning (Caro, Gomez, & Giraldo, 2017). Essentially, computational metacognition aims to harness knowledge from the operational process of human metacognition and metacognitive approaches to artificial intelligence.…”

Section: Artificial Intelligence Approaches Aspects Of Metacognitionmentioning

confidence: 99%

See 1 more Smart Citation

Strengthening AI via ToM and MC dimensions

Bamicha,

Drigas

2024

Sci. Electronic Arch

View full text Add to dashboard Cite

Theory of Mind (ToM) highlights the social-cognitive ability of the individual to communicate and interact effectively with the members of each social group. Essentially, it is the cornerstone of social knowledge that allows the recognition and understanding of the thoughts, intentions, and feelings of all involved, promoting social interaction and engagement. Metacognition (MC) is a higher mental ability of the biological mind and is characterized by the observation, control, evaluation, differentiation, and readjustment of the cognitive mechanism, aiming at its optimal performance and maintaining the homeostasis of mental, social, and emotional becoming of an organism. The rapid development of technology in recent decades has promoted the development of Artificial Intelligence (AI) intertwined with the need to integrate ToM and MC capabilities, enriching human communication. This paper investigates how the above-described human cognitive functions are involved in the conception and development of an artificial agent and their influence on human society. The conclusions suggest the importance of being able to read beliefs, emotions, and other factors, but also introspection by an intelligent system for social benefit, including the necessary ethical constraints.

show abstract

Section: Artificial Intelligence Approaches Aspects Of Metacognitionmentioning

confidence: 99%

Section: Artificial Intelligence Approaches Aspects Of Metacognitionmentioning

confidence: 99%

Strengthening AI via ToM and MC dimensions

Bamicha,

Drigas

2024

Sci. Electronic Arch

View full text Add to dashboard Cite

show abstract

Formal Representation of Introspective Reasoning Trace of a Cognitive Function in CARINA

Florez

Gomez

Piñeres

2018

2018 IEEE 17th International Conference on Cognitive Informatics &Amp; Cognitive Computing (ICCI*CC)

View full text Add to dashboard Cite

Design of metacognitive expectations of cognitive functions through ontological representations

Madera-Doval¹,

Piñeres²,

Gómez³

et al. 2018

DYNA

View full text Add to dashboard Cite

Este artículo presenta un modelo de expectativas metacognitivas sobre el tiempo de funcionamiento de las funciones cognitivas en la arquitectura metacognitiva CARINA. Se crea una representación formal y ontológica que establece la relación entre el proceso de observar un hecho en el auto-modelo y una creencia almacenada en la memoria semántica del sistema. La ontología cognitiva evidenció el proceso de búsqueda e intercambio de información entre diferentes tipos de recuerdos, tales como: memoria sensorial, memoria semántica, memoria de procedimientos, memoria prospectiva y memoria de trabajo. El experimento realizado demostró la funcionalidad del modelo en donde se generó expectativas para cada observación y podía compararlas con los valores observados en tiempo real. Otro tipo de resultado fue avance conceptual de una expectativa, la representación matemática formal, el diseño de la ontología y el modelo como un mecanismo de implementación en la arquitectura CARINA.

show abstract

Algorithmic knowledge profiles for introspective monitoring in artificial cognitive agents

Cited by 5 publications

References 18 publications

Strengthening AI via ToM and MC dimensions

Strengthening AI via ToM and MC dimensions

Formal Representation of Introspective Reasoning Trace of a Cognitive Function in CARINA

Design of metacognitive expectations of cognitive functions through ontological representations

Contact Info

Product

Resources

About