### METHOD OF UNSUPERVISED LEARNING OF HIERARCHICAL EXTRACTOR OF VISUAL FEATURES BASED ON MODIFICATION OF NEURAL GAS

#### Abstract

The modern technologies of the intellectual analysis of visual information for solving the problem of unsupervised training in real time with the aim of adapting to unknown conditions of observation are analyzed. It is proposed to use 10 layers of the well-known neural network VGG-16 as a model of the hierarchical extractor of visual features that can be used in the transfer learning tasks. The use of the principles of the neural gas to increase the convergence rate of the algorithm of usupervised learning of the extractor of visual features under the conditions of a limited amount of training data is considered. The modification of the neuron gas aimed to sparse coding of input observations is based on the optimized orthogonal matching pursuit algorithm that was used to increase the informativeness of the feature set in condition of limited sample size. Training dataset is generated by selecting from a popular image base ImageNet and selecting patches from selected images or feature maps on a given layer. The method of so-called information-extreme machine learning of decision rules is proposed for assessing the efficiency of the proposed feature extractor. Information-extreme learning is based on the use of binary coding of the feature representation of observations and the construction of radial-basic decision rules in Hamming's binary space. The implementation of the algorithm is based on the use of computationally simple operations such comparation with threshold and a bitwise XOR. Optimization of the geometric parameters of the partition feature space into separated classes is carried out in the binary space, therefore, it can be implemented by the method of a sequential direct busting with a given step, since such steps are relatively small. For optimizing parameters of encoding observations rules is used population-based particle swarm algorithm for searching global maximum of logarithmic information Kullback’s criterion in admissible domain of it function. In this case we normalized modification information criterion which is function of the first and second kind errors is used. The effectiveness of training of decision rules in the case of the use of an extractor supervise trained with by a stochastic gradient descent method, with case of supervised trained feature extractor is compared. According to the results of physical modeling unsupervised learning of extractor ensures the accuracy of decisive rules to 96.4% which is inferior to the accuracy of supervised learning which is equal to 98.7% are shown.

#### Keywords

#### Full Text:

PDF (Українська)#### References

Zhongling, H., Zongxu, P. and Bin, L. Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data. Remote Sensing, 2017, vol. 9, no. 909, pp. 2–21. Available at: http://www.mdpi.com/2072-4292/9/9/907/pdf

Masci, J., Meier, U., Ciresan, D., Schmidhuber, J. Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction. Proc. International Conference on Artificial Neural Networks (ICANN 2011), 2011, pp. 52–59. DOI:10.1007/978-3-642-21735-7_7.

Labusch, K., Barth, E., Martinetz, Th. Learning Data Representations with Sparse Coding Neural Gas. Proc. 16th European Symposium on Artificial Neural Networks, 2008, pp. 233–238. DOI: 10.1007/978-3-540-87536-9_81.

Labusch, K., Barth, E., Martinetz, Th. Sparse Coding Neural Gas: Learning of Overcomplete Data Representations. Neurocomputing, 2009, vol. 72, i. 7–9, pp. 1547–1555. DOI:10.1016/j.neucom.2008.11.027.

Rizhova, A.S., Moskalenko, V. V., Dovbysh, А. S. Information Extreme Method for Classification of observations with categorical attributes. Cybernetics and Systems Analysis, 2016, vol.52, no. 2, pp. 56–63. DOI:10.1007/s1055.

Moskalenko, V. V., Pimonenko, S. V. Optimizing the parameters of functioning of the system of management of data center it infrastructure. Eastern-European journal of enterprise technologies, 2016, vol. 5, no. 2 (83), pp. 21–29. DOI: 10.15587/1729-4061.2016.79231.

Ng, H.-W., Dung Nguyen, V., Vonikakis, V., Winkler, S. Deep Learning for Emotion Recognition on Small Datasets Using Transfer Learning. Proc. 17th International Conference on Multimodal Interaction (ICMI’15), 2015, pp. 443-449. DOI:10.1145/2818346.2830593.

Simonyan, K., Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. Proc. 3rd International Conference on Learning Representations (ICLR2015), 2015, pp. 1–14.

### Refbacks

- There are currently no refbacks.