Online Services Based on Neural Networks: a Review of Modern Implementations

Vladimir Ilyin

Abstract


The review presents the results of an analysis of six online services based on neural networks (NN-services), which are designed to generate texts, images, videos and websites; search the Internet and answer questions. A brief overview of the functionality of the NN-services is provided. Based on the analysis, it is suggested to enhance statistical approaches in neural network technology development by incorporating methods for training neural networks and interpreting queries using S-symbolic models of concept systems.The proposed methods have been tested in automated parallel program design systems that utilize task knowledge systems.


Full Text:

PDF

References


Walter, W. G. 1953. The living brain. New York, Norton. 311 p.

Freeman, W. J. 1986. W. G. Walter: The Living Brain. In: Palm G., Aertsen A. (eds). Brain Theory. Springer, Berlin, Heidelberg. DOI: 10.1007/978-3-642-70911-1_17.

Kriesel, D. A. 2007. Brief Introduction to Neural Networks. 244 p. http://www.dkriesel.com.

Ilyin, V. D. 2022. Symbolic Modeling (S-Modeling): an Introduction to Theory // Artificial Intelligence Trends in Systems, CSOC 2022 / Ed. R. Silhavy. – Lecture Notes in Networks and Systems ser. – Cham: Springer, 2022. Vol. 502. P. 585–591. DOI: 10.1007/978-3-031-09076-9_54.

Ilyin, V. D. 2023. Teoriya S-simvolov: formalizatsiya znaniy ob S-zadachakh [Theory of S-symbols: Formalization of Knowledge about S-problems] Sistemy i Sredstva Informatiki [Systems and Means of Informatics], 33(1), 124–131. DOI: 10.14357/08696527230212 .

Neural Network Primitives Part 1 – McCulloch Pitts Neuron Model (1943). 2020. Deep Learning Basics. https://machinelearningknowledge.ai/mcculloch-pitts-neuron-model/.

De La Cruz, R. 2024. Frank Rosenblatt’s Perceptron, Birth of The Neural Network. https://readmedium.com/frank-rosenblatts-perceptron-19fcce9d627f.

Haykin, S. 2008. Neural Networks and Learning Machines. 936 p. Pearson. ISBN: 978-0131471399.

Zhang, X. J., Moore, J. M., Yan, G. et al. 2023. Universal structural patterns in sparse recurrent neural networks. Commun Phys 6, 243. DOI: 10.1038/s42005-023-01364-0.

Wegner, S. A. 2024. Neural Networks. In: Mathematical Introduction to Data Science. Springer, Berlin, Heidelberg. DOI: 10.1007/978-3-662-69426-8_16.

Yu, W., Guo, H., Xiao, J. et al. 2024. Physical neural networks with self-learning capabilities. Sci. China Phys. Mech. Astron. 67, 287501. DOI: 10.1007/s11433-024-2403-x.

Ortega-Fernandez, I., Sestelo, M., and N. M. Villanueva. 2024. Explainable generalized additive neural networks with independent neural network training. Stat Comput 34, 6. DOI: 10.1007/s11222-023-10320-5.

Pira, L., and C. Ferrie. 2024. On the interpretability of quantum neural networks. Quantum Mach. Intell. 6, 52. DOI: 10.1007/s42484-024-00191-y.

Ilyin, V.D. 1995. A methodology for knowledge based engineering of parallel program systems. In: Forsyth, G.F., Ali, M. (eds.) Proceedings of the Eighth International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, Melbourne, Australia, Jun 06-08, 1995 (IEA/AIE-95). pp. 805–809. Gordon and Breach Publishers, Melbourne.

Ilyin, A. V., and V. D. Ilyin. 2021. Updated Methodology for Task Knowledge Based Development of Parallel Programs. In: Silhavy, R., Silhavy, P., Prokopova, Z. (eds) Data Science and Intelligent Systems. CoMeSySo 2021. Lecture Notes in Networks and Systems, vol 231. Springer, Cham. DOI: 10.1007/978-3-030-90321-3_25.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность IT Congress 2024

ISSN: 2307-8162