Neural Networks
Recently Published Documents


(FIVE YEARS 55537)



2022 ◽  
Vol 16 (1) ◽  
pp. 1-20
Ping Zhao ◽  
Zhijie Fan* ◽  
Zhiwei Cao ◽  
Xin Li

In order to improve the ability to detect network attacks, traditional intrusion detection models often used convolutional neural networks to encode spatial information or recurrent neural networks to obtain temporal features of the data. Some models combined the two methods to extract spatio-temporal features. However, these approaches used separate models and learned features insufficiently. This paper presented an improved model based on temporal convolutional networks (TCN) and attention mechanism. The causal and dilation convolution can capture the spatio-temporal dependencies of the data. The residual blocks allow the network to transfer information in a cross-layered manner, enabling in-depth network learning. Meanwhile, attention mechanism can enhance the model's attention to the relevant anomalous features of different attacks. Finally, this paper compared models results on the KDD CUP99 and UNSW-NB15 datasets. Besides, the authors apply the model to video surveillance network attack detection scenarios. The result shows that the model has advantages in evaluation metrics.

2022 ◽  
Vol 133 ◽  
pp. 104026
Wen Gao ◽  
Xuanming Zhang ◽  
Qiushi He ◽  
Borong Lin ◽  
Weixin Huang

2021 ◽  
Vol 8 ◽  
Dmitry Viatkin ◽  
Begonya Garcia-Zapirain ◽  
Amaia Méndez-Zorrilla ◽  
Maxim Zakharov

This paper proposes a novel neural network architecture and its ensembles to predict the critical superconductivity temperature of materials based on their chemical formula. The research describes the methods and processes of extracting data from the chemical formula and preparing these extracted data for use in neural network training using TensorFlow. In our approach, recurrent neural networks are used including long short-term memory layers and neural networks based on one-dimensional convolution layers for data analysis. The proposed model is an ensemble of pre-trained neural network architectures for the prediction of the critical temperature of superconductors based on their chemical formula. The architecture of seven pre-trained neural networks is based on the long short-term memory layers and convolution layers. In the final ensemble, six neural networks are used: one network based on LSTM and four based on convolutional neural networks, and one embedding ensemble of convolution neural networks. LSTM neural network and convolution neural network were trained in 300 epochs. Ensembles of models were trained in 20 epochs. All neural networks are trained in two stages. At both stages, the optimizer Adam was used. In the first stage, training was carried out by the function of losses Mean Absolute Error (MAE) with the value of optimizer learning rate equal to 0.001. In the second stage, the previously trained model was trained by the function of losses Mean Squared Error (MSE) with a learning rate equal to 0.0001. The final ensemble is trained with a learning rate equal to 0.00001. The final ensemble model has the following accuracy values: MAE is 4.068, MSE is 67.272, and the coefficient of determination (R2) is 0.923. The final model can predict the critical temperature for the chemistry formula with an accuracy of 4.068°.

2021 ◽  
Vol 22 (1) ◽  
Ramin Hasibi ◽  
Tom Michoel

Abstract Background Molecular interaction networks summarize complex biological processes as graphs, whose structure is informative of biological function at multiple scales. Simultaneously, omics technologies measure the variation or activity of genes, proteins, or metabolites across individuals or experimental conditions. Integrating the complementary viewpoints of biological networks and omics data is an important task in bioinformatics, but existing methods treat networks as discrete structures, which are intrinsically difficult to integrate with continuous node features or activity measures. Graph neural networks map graph nodes into a low-dimensional vector space representation, and can be trained to preserve both the local graph structure and the similarity between node features. Results We studied the representation of transcriptional, protein–protein and genetic interaction networks in E. coli and mouse using graph neural networks. We found that such representations explain a large proportion of variation in gene expression data, and that using gene expression data as node features improves the reconstruction of the graph from the embedding. We further proposed a new end-to-end Graph Feature Auto-Encoder framework for the prediction of node features utilizing the structure of the gene networks, which is trained on the feature prediction task, and showed that it performs better at predicting unobserved node features than regular MultiLayer Perceptrons. When applied to the problem of imputing missing data in single-cell RNAseq data, the Graph Feature Auto-Encoder utilizing our new graph convolution layer called FeatGraphConv outperformed a state-of-the-art imputation method that does not use protein interaction information, showing the benefit of integrating biological networks and omics data with our proposed approach. Conclusion Our proposed Graph Feature Auto-Encoder framework is a powerful approach for integrating and exploiting the close relation between molecular interaction networks and functional genomics data.

Maxim Secor ◽  
Alexander V. Soudackov ◽  
Sharon Hammes-Schiffer

Sign in / Sign up

Export Citation Format

Share Document