Binary and Multiclass Text Classification by Means of Separable Convolutional Neural Network
| Autor: | E. B. Solovyeva, Ali Abdullah |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Technological innovations. Automation
text classification Computer science neural network separable convolutional neural network Binary number Convolutional neural network Separable space natural language processing Artificial neural network business.industry Deep learning HD45-45.2 General Engineering deep learning Pattern recognition Sigmoid function TA213-215 Engineering machinery tools and implements Recurrent neural network ComputingMethodologies_PATTERNRECOGNITION machine learning Softmax function nonlinear model Artificial intelligence business |
| Zdroj: | Inventions Volume 6 Issue 4 Inventions, Vol 6, Iss 70, p 70 (2021) |
| ISSN: | 2411-5134 |
| DOI: | 10.3390/inventions6040070 |
| Popis: | In this paper, the structure of a separable convolutional neural network that consists of an embedding layer, separable convolutional layers, convolutional layer and global average pooling is represented for binary and multiclass text classifications. The advantage of the proposed structure is the absence of multiple fully connected layers, which is used to increase the classification accuracy but raises the computational cost. The combination of low-cost separable convolutional layers and a convolutional layer is proposed to gain high accuracy and, simultaneously, to reduce the complexity of neural classifiers. Advantages are demonstrated at binary and multiclass classifications of written texts by means of the proposed networks under the sigmoid and Softmax activation functions in convolutional layer. At binary and multiclass classifications, the accuracy obtained by separable convolutional neural networks is higher in comparison with some investigated types of recurrent neural networks and fully connected networks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|