Applying Fuzziness in Neural Symbolic-Integration
This paper presents a new approach to upgrade the performance of logic programming in Hopfield network by applying fuzziness in the system. Fuzzy Hopfield neural network clustering technique is used as it can solve the combinatorial optimization problems that always occur in Hopfield network. Neural...
| Main Authors: | , |
|---|---|
| Format: | Working Paper |
| Language: | English |
| Published: |
School of Mathematical Sciences, USM
2012
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/758/ http://ir.unimas.my/id/eprint/758/1/Applying%20Fuzziness%20in%20Neural%20Symbolic-Integration%20%28abstract%29.pdf |
| _version_ | 1848834611329630208 |
|---|---|
| author | Farah Liyana, Azizan Sathasivam, Saratha |
| author_facet | Farah Liyana, Azizan Sathasivam, Saratha |
| author_sort | Farah Liyana, Azizan |
| building | UNIMAS Institutional Repository |
| collection | Online Access |
| description | This paper presents a new approach to upgrade the performance of logic programming in Hopfield network by applying fuzziness in the system. Fuzzy Hopfield neural network clustering technique is used as it can solve the combinatorial optimization problems that always occur in Hopfield network. Neural networks are networks of neurons as the information processing paradigm that is inspired by the way biological nervous system, such as brain, process information while logic describes relationship among propositions. Logic requires descriptive symbolic tools whereas for neural networks are non-symbolic form. By neural-logic integration, the advantages of both neural network and logic programming can be combined. This work is merely focusing on the ways to upgrade the performance of logic programming in Hopfield network. We carried out computer simulations to demonstrate the ability of fuzzy Hopfield neural network clustering technique in enhancing the performance of the system. By applying fuzzy Hopfield neural network clustering technique in the system, it does not only produce better quality solutions but it also can handle the network better even though the complexity increased. Besides that, the system also makes the solutions converge faster. Thus, the presence of this fuzzy Hopfield neural network clustering technique in the system will produce solutions with better quality. |
| first_indexed | 2025-11-15T05:54:44Z |
| format | Working Paper |
| id | unimas-758 |
| institution | Universiti Malaysia Sarawak |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T05:54:44Z |
| publishDate | 2012 |
| publisher | School of Mathematical Sciences, USM |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | unimas-7582020-08-14T01:47:46Z http://ir.unimas.my/id/eprint/758/ Applying Fuzziness in Neural Symbolic-Integration Farah Liyana, Azizan Sathasivam, Saratha QA Mathematics QA75 Electronic computers. Computer science This paper presents a new approach to upgrade the performance of logic programming in Hopfield network by applying fuzziness in the system. Fuzzy Hopfield neural network clustering technique is used as it can solve the combinatorial optimization problems that always occur in Hopfield network. Neural networks are networks of neurons as the information processing paradigm that is inspired by the way biological nervous system, such as brain, process information while logic describes relationship among propositions. Logic requires descriptive symbolic tools whereas for neural networks are non-symbolic form. By neural-logic integration, the advantages of both neural network and logic programming can be combined. This work is merely focusing on the ways to upgrade the performance of logic programming in Hopfield network. We carried out computer simulations to demonstrate the ability of fuzzy Hopfield neural network clustering technique in enhancing the performance of the system. By applying fuzzy Hopfield neural network clustering technique in the system, it does not only produce better quality solutions but it also can handle the network better even though the complexity increased. Besides that, the system also makes the solutions converge faster. Thus, the presence of this fuzzy Hopfield neural network clustering technique in the system will produce solutions with better quality. School of Mathematical Sciences, USM 2012 Working Paper NonPeerReviewed text en http://ir.unimas.my/id/eprint/758/1/Applying%20Fuzziness%20in%20Neural%20Symbolic-Integration%20%28abstract%29.pdf Farah Liyana, Azizan and Sathasivam, Saratha (2012) Applying Fuzziness in Neural Symbolic-Integration. [Working Paper] |
| spellingShingle | QA Mathematics QA75 Electronic computers. Computer science Farah Liyana, Azizan Sathasivam, Saratha Applying Fuzziness in Neural Symbolic-Integration |
| title | Applying Fuzziness in Neural Symbolic-Integration |
| title_full | Applying Fuzziness in Neural Symbolic-Integration |
| title_fullStr | Applying Fuzziness in Neural Symbolic-Integration |
| title_full_unstemmed | Applying Fuzziness in Neural Symbolic-Integration |
| title_short | Applying Fuzziness in Neural Symbolic-Integration |
| title_sort | applying fuzziness in neural symbolic-integration |
| topic | QA Mathematics QA75 Electronic computers. Computer science |
| url | http://ir.unimas.my/id/eprint/758/ http://ir.unimas.my/id/eprint/758/1/Applying%20Fuzziness%20in%20Neural%20Symbolic-Integration%20%28abstract%29.pdf |