Lógica para Informática

La Inteligencia Artificial está a punto de cambiar nuestras vidas. Todos los sectores se verán implicados, incluida la enseñanza del Derecho. En este punto, uno de los métodos introducidos ha sido los Sistemas de Expertos, programas capaces de resolver los problemas jurídicos de manera interactiva a través de una lógica determinada. Aunque de escaso estudio en nuestro país, los SEJ aspiran a convertirse en una herramienta muy útil para el aprendizaje de determinadas habilidades jurídicas. Para facilitar su comprensión, el presente artículo propone resolver un caso práctico de derechos reales utilizando la lógica subyacente al SEJ con el objetivo de visibilizar sus fallas y virtudes.

show abstract

Rule Extraction in Trained Feedforward Deep Neural Networks

Negro,

Pons

2024

International Journal of Artificial Intelligence and Machine Learning

View full text Add to dashboard Cite

Explainability is a key aspect of machine learning, necessary for ensuring transparency and trust in decision-making processes. As machine learning models become more complex, the integration of neural and symbolic approaches has emerged as a promising solution to the explainability problem. One effective solution involves using search techniques to extract rules from trained deep neural networks by examining weight and bias values and calculating their correlation with outputs. This article proposes incorporating cosine similarity in this process to narrow down the search space and identify the critical path connecting inputs to final results. Additionally, the integration of first-order logic (FOL) is suggested to provide a more comprehensive and interpretable understanding of the decision-making process. By leveraging cosine similarity and FOL, an innovative algorithm capable of extracting and explaining rule patterns learned by a feedforward trained neural network was developed and tested in two use cases, demonstrating its effectiveness in providing insights into model behavior.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Lógica para Informática

Cited by 4 publications

References 0 publications

An Algorithm to Belief Revision and to Verify Consistency of a Knowledge Base

An Algorithm to Belief Revision and to Verify Consistency of a Knowledge Base

La aplicación de los SEJ (Sistemas de Expertos Jurídicos) en la educación: propuesta en un caso práctico de Derecho Privado

Rule Extraction in Trained Feedforward Deep Neural Networks

Contact Info

Product

Resources

About