Combining Architectures for Temporal Learning in Neural-Symbolic Systems

Borges, Rafael V.; Lamb, Luís C.; Garcez, Artur S. d’Avila

doi:10.1109/his.2006.264929

Cited by 2 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Como solución a este problema de datos insuficientes o incompletos en Borges et al, 2006 se plantea la inserción de conocimientos previos donde advierten que, en todos los casos, las redes lograron un desempeño efectivo al aprender operadores temporales.…”

Section: Ineficiencia De Datosunclassified

“…En el trabajo presentado por Borges et al, (2006), los autores proponen una arquitectura que combina redes neuronales recurrentes de entrada-salida y un sistema neural-simbólico para el aprendizaje de conocimiento simbólico temporal. Mediante un enfoque experimental, han demostrado que la integración del conocimiento simbólico puede mejorar las características de una red neuronal, en particular la tolerancia al ruido, rendimiento y convergencia de un algoritmo de aprendizaje.…”

Section: Acelerar El Aprendizajeunclassified

“…Para aprender actividades de reconocimiento e imitación de secuencias y series temporales aplicadas a robótica, Xie et al, (2021) aplican lógica temporal lineal (LTL), para tareas de Predicción. Borges et al, (2006) presentan un framework de aplicación general para realizar predicciones, utilizando lógica proposicional.…”

Section: Lógica Temporal Linealunclassified

See 2 more Smart Citations

Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literature

Negro¹,

Pons²

2022

View full text Add to dashboard Cite

The need for neural-symbolic integration becomes apparent as more complex problems are tackled, and they go beyond limited domain tasks such as classification. In this sense, understanding the state of the art of hybrid technologies based on Deep Learning and augmented with logic based systems, is of utmost importance. As a consequence, we seek to understand and represent the current state of these technologies that are highly used in intelligent systems engineering.This work aims to provide a comprehensive view of the solutions available in the literature, within the field of applied Artificial Intelligence (AI), using technologies based on AI techniques that integrate symbolic and non-symbolic logic (in particular artificial neural networks), making them the subject of a systematic literature review (SLR). The resulting technologies are discussed and evaluated from both perspectives: symbolic and non-symbolic AI.In this work, we use the PICOC & Limits method to define the research questions and analyze the results.Out of a total of 65 candidate studies found, 24 articles (37%) relevant to this study were selected. Each study also focuses on different application domains. Conclusion: Through the analysis of the selected works throughout this review, we have seen different combinations of logical systems with some form of neural network and, although we have not found a clear architectural pattern, efforts to find a model of general purpose combining both worlds drive trends and research efforts.

show abstract

Section: Ineficiencia De Datosunclassified

Section: Acelerar El Aprendizajeunclassified