Similarity Measures for Learning in Lattice Based Biomimetic Neural Networks
This paper presents a novel lattice based biomimetic neural network trained by means of a similarity measure derived from a lattice positive valuation. For a wide class of pattern recognition problems, the proposed artificial neural network, implemented as a dendritic hetero-associative memory deliv...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/8/9/1439 |
| _version_ | 1827707415621009408 |
|---|---|
| author | Gerhard X. Ritter Gonzalo Urcid Luis-David Lara-Rodríguez |
| author_facet | Gerhard X. Ritter Gonzalo Urcid Luis-David Lara-Rodríguez |
| author_sort | Gerhard X. Ritter |
| collection | DOAJ |
| description | This paper presents a novel lattice based biomimetic neural network trained by means of a similarity measure derived from a lattice positive valuation. For a wide class of pattern recognition problems, the proposed artificial neural network, implemented as a dendritic hetero-associative memory delivers high percentages of successful classification. The memory is a feedforward dendritic network whose arithmetical operations are based on lattice algebra and can be applied to real multivalued inputs. In this approach, the realization of recognition tasks, shows the inherent capability of prototype-class pattern associations in a fast and straightforward manner without need of any iterative scheme subject to issues about convergence. Using an artificially designed data set we show how the proposed trained neural net classifies a test input pattern. Application to a few typical real-world data sets illustrate the overall network classification performance using different training and testing sample subsets generated randomly. |
| first_indexed | 2024-03-10T16:46:18Z |
| format | Article |
| id | doaj.art-e900f197b07a4296af3c3d10b14ab934 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T16:46:18Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-e900f197b07a4296af3c3d10b14ab9342023-11-20T11:35:57ZengMDPI AGMathematics2227-73902020-08-0189143910.3390/math8091439Similarity Measures for Learning in Lattice Based Biomimetic Neural NetworksGerhard X. Ritter0Gonzalo Urcid1Luis-David Lara-Rodríguez2Computer & Information Science and Engineering Department, University of Florida (UF), Gainesville, FL 72410, USAOptics Department, National Institute of Astrophysics, Optics and Electronics (INAOE), Tonantzintla, Puebla 72840, MexicoMechatronics Engineering Department, Politechnic University of Puebla (UPP), Cuanalá, Puebla 72640, MexicoThis paper presents a novel lattice based biomimetic neural network trained by means of a similarity measure derived from a lattice positive valuation. For a wide class of pattern recognition problems, the proposed artificial neural network, implemented as a dendritic hetero-associative memory delivers high percentages of successful classification. The memory is a feedforward dendritic network whose arithmetical operations are based on lattice algebra and can be applied to real multivalued inputs. In this approach, the realization of recognition tasks, shows the inherent capability of prototype-class pattern associations in a fast and straightforward manner without need of any iterative scheme subject to issues about convergence. Using an artificially designed data set we show how the proposed trained neural net classifies a test input pattern. Application to a few typical real-world data sets illustrate the overall network classification performance using different training and testing sample subsets generated randomly.https://www.mdpi.com/2227-7390/8/9/1439biomimetic neural networksdendritic computinglattice neural networkslattice valuationspattern recognitionsimilarity measures |
| spellingShingle | Gerhard X. Ritter Gonzalo Urcid Luis-David Lara-Rodríguez Similarity Measures for Learning in Lattice Based Biomimetic Neural Networks Mathematics biomimetic neural networks dendritic computing lattice neural networks lattice valuations pattern recognition similarity measures |
| title | Similarity Measures for Learning in Lattice Based Biomimetic Neural Networks |
| title_full | Similarity Measures for Learning in Lattice Based Biomimetic Neural Networks |
| title_fullStr | Similarity Measures for Learning in Lattice Based Biomimetic Neural Networks |
| title_full_unstemmed | Similarity Measures for Learning in Lattice Based Biomimetic Neural Networks |
| title_short | Similarity Measures for Learning in Lattice Based Biomimetic Neural Networks |
| title_sort | similarity measures for learning in lattice based biomimetic neural networks |
| topic | biomimetic neural networks dendritic computing lattice neural networks lattice valuations pattern recognition similarity measures |
| url | https://www.mdpi.com/2227-7390/8/9/1439 |
| work_keys_str_mv | AT gerhardxritter similaritymeasuresforlearninginlatticebasedbiomimeticneuralnetworks AT gonzalourcid similaritymeasuresforlearninginlatticebasedbiomimeticneuralnetworks AT luisdavidlararodriguez similaritymeasuresforlearninginlatticebasedbiomimeticneuralnetworks |