Neural network model of heteroassociative memory for the classification task
The subject of study in this article is the features of structural organization and functioning of the improved Hamming network as a model of neural network heteroassociative memory for classification by discriminant functions. The goal is to improve the neural network classifier based on the Hammin...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
National Aerospace University «Kharkiv Aviation Institute»
2022-05-01
|
| Series: | Радіоелектронні і комп'ютерні системи |
| Subjects: | |
| Online Access: | http://nti.khai.edu/ojs/index.php/reks/article/view/1705 |
| _version_ | 1797705366409052160 |
|---|---|
| author | Tatiana Martyniuk Bohdan Krukivskyi Leonid Kupershtein Vitaliy Lukichov |
| author_facet | Tatiana Martyniuk Bohdan Krukivskyi Leonid Kupershtein Vitaliy Lukichov |
| author_sort | Tatiana Martyniuk |
| collection | DOAJ |
| description | The subject of study in this article is the features of structural organization and functioning of the improved Hamming network as a model of neural network heteroassociative memory for classification by discriminant functions. The goal is to improve the neural network classifier based on the Hamming network, which implements the criterion of maximum similarity using discriminant functions and does not have restrictions on the representation of input data (not only binary data). The tasks: analyze the capabilities of associative memory models using neural networks as an example; analyze the features of classification on the principles of discriminant analysis; develop the structure of a neural network classifier as a model of neural network heteroassociative memory; perform simulation modeling of the classification process on the example of medical diagnosis. The methods used are a mathematical model of the functioning of a neural network as a classifier, and simulation in C#. The following results have been obtained: the structure of the neural network classifier has been improved through the formation connection matrix of a hidden layer from pre-calculated coefficients of linear discriminant functions, and the connection matrix of the output layer in the form symmetrical matrix with zeros on the main diagonal. This allows not only to simplify m connections, where m is the number of classes, in the structure of the output layer of the neural network classifier, but also to speed up the classification process, as well as to implement classification by the maximum of discriminant functions. Conclusions. The scientific novelty of the results obtained is as follows: the neural network classification method has been improved using pre-calculated elements of the connection matrices in the hidden and output layers of the classifier, which does not imply a long process of direct neural network learning with using discriminant functions; the structural organization of a neural network classifier is proposed, which is an improvement of the Hamming network as a model of heteroassociative memory, that allows using this classifier in a decision support system for medical diagnosis; the removal of positive feedback in neurons of the competitive (output) layer is implemented, which allows not only simplifies the structure of the neural network classifier but also speeds up the classification process almost 2 times, which is confirmed by the simulation results. |
| first_indexed | 2024-03-12T05:35:04Z |
| format | Article |
| id | doaj.art-1536d77f1f754bf5acd3fd246ab48e6d |
| institution | Directory Open Access Journal |
| issn | 1814-4225 2663-2012 |
| language | English |
| last_indexed | 2024-03-12T05:35:04Z |
| publishDate | 2022-05-01 |
| publisher | National Aerospace University «Kharkiv Aviation Institute» |
| record_format | Article |
| series | Радіоелектронні і комп'ютерні системи |
| spelling | doaj.art-1536d77f1f754bf5acd3fd246ab48e6d2023-09-03T06:30:45ZengNational Aerospace University «Kharkiv Aviation Institute»Радіоелектронні і комп'ютерні системи1814-42252663-20122022-05-010210811710.32620/reks.2022.2.091682Neural network model of heteroassociative memory for the classification taskTatiana Martyniuk0Bohdan Krukivskyi1Leonid Kupershtein2Vitaliy Lukichov3Vinnytsia National Technical University, VinnytsiaVinnytsia National Technical University, VinnytsiaVinnytsia National Technical University, VinnytsiaVinnytsia National Technical University, VinnytsiaThe subject of study in this article is the features of structural organization and functioning of the improved Hamming network as a model of neural network heteroassociative memory for classification by discriminant functions. The goal is to improve the neural network classifier based on the Hamming network, which implements the criterion of maximum similarity using discriminant functions and does not have restrictions on the representation of input data (not only binary data). The tasks: analyze the capabilities of associative memory models using neural networks as an example; analyze the features of classification on the principles of discriminant analysis; develop the structure of a neural network classifier as a model of neural network heteroassociative memory; perform simulation modeling of the classification process on the example of medical diagnosis. The methods used are a mathematical model of the functioning of a neural network as a classifier, and simulation in C#. The following results have been obtained: the structure of the neural network classifier has been improved through the formation connection matrix of a hidden layer from pre-calculated coefficients of linear discriminant functions, and the connection matrix of the output layer in the form symmetrical matrix with zeros on the main diagonal. This allows not only to simplify m connections, where m is the number of classes, in the structure of the output layer of the neural network classifier, but also to speed up the classification process, as well as to implement classification by the maximum of discriminant functions. Conclusions. The scientific novelty of the results obtained is as follows: the neural network classification method has been improved using pre-calculated elements of the connection matrices in the hidden and output layers of the classifier, which does not imply a long process of direct neural network learning with using discriminant functions; the structural organization of a neural network classifier is proposed, which is an improvement of the Hamming network as a model of heteroassociative memory, that allows using this classifier in a decision support system for medical diagnosis; the removal of positive feedback in neurons of the competitive (output) layer is implemented, which allows not only simplifies the structure of the neural network classifier but also speeds up the classification process almost 2 times, which is confirmed by the simulation results.http://nti.khai.edu/ojs/index.php/reks/article/view/1705heteroassociative memoryneural network classifierclassificationlinear discriminant function |
| spellingShingle | Tatiana Martyniuk Bohdan Krukivskyi Leonid Kupershtein Vitaliy Lukichov Neural network model of heteroassociative memory for the classification task Радіоелектронні і комп'ютерні системи heteroassociative memory neural network classifier classification linear discriminant function |
| title | Neural network model of heteroassociative memory for the classification task |
| title_full | Neural network model of heteroassociative memory for the classification task |
| title_fullStr | Neural network model of heteroassociative memory for the classification task |
| title_full_unstemmed | Neural network model of heteroassociative memory for the classification task |
| title_short | Neural network model of heteroassociative memory for the classification task |
| title_sort | neural network model of heteroassociative memory for the classification task |
| topic | heteroassociative memory neural network classifier classification linear discriminant function |
| url | http://nti.khai.edu/ojs/index.php/reks/article/view/1705 |
| work_keys_str_mv | AT tatianamartyniuk neuralnetworkmodelofheteroassociativememoryfortheclassificationtask AT bohdankrukivskyi neuralnetworkmodelofheteroassociativememoryfortheclassificationtask AT leonidkupershtein neuralnetworkmodelofheteroassociativememoryfortheclassificationtask AT vitaliylukichov neuralnetworkmodelofheteroassociativememoryfortheclassificationtask |