Compilation of Symbolic Knowledge and Integration with Numeric Knowledge Using Hybrid Systems

Sánchez, Vianey Guadalupe Cruz; Salgado, Gerardo Reyes; Villegas, Osslan Osiris Vergara; Pérez-Ortega, Joaquín; Rendón, Azucena Montes

doi:10.1007/11579427_2

Cited by 2 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural-Symbolic Hybrid Systems are systems based on artificial neural networks that also interact with symbolic components (Cloete & Zurada, 2000). These types of systems integrate the connectionist and symbolic knowledge, in such a way that the knowledge contained in each one of these is complemented (Cruz, Reyes, Vergara, Perez, & Montes, 2005;Cruz, Reyes, Vergara, & Pinto, 2006;Negnevitsky, 2005;Santos, 1998).…”

Section: Neural-symbolic Hybrid Systemsmentioning

confidence: 99%

“…Neural-Symbolic Hybrid Systems have received great attention and they have been used in application areas where the existence of faults can be expensive, such as engineering, manufacturing, science, business (Cruz, Reyes, Vergara, Perez, & Montes, 2005;Cruz, Reyes, Vergara, & Pinto, 2006;Santos, 1998) and cognitive informatics and cognitive computing (Wang, 2003(Wang, , 2008. The NSHS combine symbolic knowledge (rules or frames, mainly) and connectionist (neural networks).…”

Section: Introductionmentioning

confidence: 99%

“…The knowledge contained in a NSHS comes from practical and theoretical sources and may contain errors. Errors occur due to data nature and to integration results from different representations (Cruz, Reyes, Vergara, Perez, & Montes, 2005;Villanueva, Cruz, Reyes, & Benítez, 2006). The previous statement is due to Rule-Based Systems (RBS) whose use is made consulting with several experts and may have conflicting experiences; on the other hand the examples of connectionist approach might be redundant due to a wrong selection.…”

Section: Introductionmentioning

confidence: 99%

“…The previous statement is due to Rule-Based Systems (RBS) whose use is made consulting with several experts and may have conflicting experiences; on the other hand the examples of connectionist approach might be redundant due to a wrong selection. Therefore, verification and validation of extracted knowledge from a NSHS allows the knowledge engineer to make decisions in the construction of the same one (Cruz, 2004;Cruz, Reyes, Vergara, Perez, & Montes, 2005;Santos, 1998).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Enhanced Petri Net Model to Verify and Validate a Neural-Symbolic Hybrid System

Jorge¹,

Salgado²,

Sánchez³

2009

International Journal of Software Science and Computational Intelligence

View full text Add to dashboard Cite

As the Neural-Symbolic Hybrid Systems (NSHS) gain acceptance, it increases the necessity to guarantee the automatic validation and verification of the knowledge contained in them. In the past, such processes were made manually. In this article, an enhanced Petri net model is presented to the detection and elimination of structural anomalies in the knowledge base of the NSHS. In addition, a reachability model is proposed to evaluate the obtained results of the system versus the expected results by the user. The validation and verification method is divided in two stages: 1) it consists of three phases: rule normalization, rule modeling and rule verification. 2) It consists of three phases: rule modeling, dynamic modeling and evaluation of results. Such method is useful to ensure that the results of a NSHS are correct. Examples are presented to demonstrate the effectiveness of the results obtained with the method.

show abstract

Section: Neural-symbolic Hybrid Systemsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Enhanced Petri Net Model to Verify and Validate a Neural-Symbolic Hybrid System

Jorge¹,

Salgado²,

Sánchez³

2009

International Journal of Software Science and Computational Intelligence

View full text Add to dashboard Cite

show abstract

Verification and validation of a Neural-Symbolic Hybrid System using an enhanced Petri net

Jorge¹,

Salgado²,

Sánchez³

2008

2008 7th IEEE International Conference on Cognitive Informatics

Self Cite

View full text Add to dashboard Cite

As the Neural-Symbolic Hybrid Systems (NSHS) gain acceptance, it increases the necessity to guarantee the automatic validation and verification of the knowledge contained in them. In the past, such processes were made manually.In this paper, an enhanced Petri net model is presented to the detection and elimination ofstructural anomalies in the knowledge base of the NSHS. In addition, a reachability model is proposed to evaluate the obtained results of the system versus the expected results by the user.The validation and verification method is divided in two stages: 1) it consists of three phases: rule normalization, rule modeling and rule verification. 2) It consists of three phases: rule modeling, dynamic modeling and evaluation of results. Such method is useful to ensure that the results ofa NSHS are correct.Examples are presented to demonstrate the effectiveness ofthe results obtained with the method.Proc. 7th IEEE Inl Conf. on Cognitive Informatics (ICCI'08)

show abstract

Compilation of Symbolic Knowledge and Integration with Numeric Knowledge Using Hybrid Systems

Cited by 2 publications

References 2 publications

An Enhanced Petri Net Model to Verify and Validate a Neural-Symbolic Hybrid System

An Enhanced Petri Net Model to Verify and Validate a Neural-Symbolic Hybrid System

Verification and validation of a Neural-Symbolic Hybrid System using an enhanced Petri net

Contact Info

Product

Resources

About