Application of deep learning technology for creating intellectual autonomous machines

O.S. Bilokon


One of the most common tasks that arise in building intelligent machine vision systems for intellectually autonomous machines is the problems of classification and regression. Classification problems are used for the reflexive action of autonomous machines. Prediction tasks can be used to build machine vision systems to provide intelligent autonomous machines with environmental knowledge, which in turn is important for planned predictable movements. Defining a class of task instances is an important procedure for the effective design of deep learning systems. In this context, the possibility of using a multilayered neural network as a regressor to construct elementary functional mappings is explored for further prediction. The study outlines the peculiarities of functioning and configuration of a specialized robotics system, considered in this paper as an intelligent autonomous machine or physical agent, generates a set of data points for elementary functions, analytical modeling and modeling of training systems. Input graph was constructed, neural network architecture was defined, gradient descent algorithm was implemented, and output schedules were finally constructed: learning process, results prediction and comparative graph of predicted results superimposed on the input graph. As a result of the study, an assessment of the machine's intellectual ability to predict was made.

Problems in programming 2020; 2-3: 407-418


neural networks; deep learning; robotic systems; autonomous intellectual machines; physical agents, regression

Full Text:

PDF (Ukrainian)


Brookshear J. Glenn, Brylow Dennis. Computer science an overview. Basic course, 13th ed.: Per. from English. St. Petersburg.: Dialectics LLC, 2019. 1104 p.: ill. Parl. Titus. English.

Khaykin Simon. Neural networks: full course, 2nd ed.: Transl. From English. St. Petersburg.: Dialectics LLC, 2019. 1104 p.: ill. Parl. Titus. English.

Akhterov A.V., Kirilchenko A.A. Fundamentals of Theoretical Robotics. Artificial neural networks. Overview. KIAM Preprints M.V. Keldysh. 2008. N 2. 20 p. URL:

Joshi, Prateek. Artificial intelligence with Python. : Per. from English. SPb. : LLC “Dialectics”, 2019. 448 p. Paral. tit. English.

Draper N., Smith G. Applied regression analysis: In 2 kn, Kn, 1 / Per, from English, - 2nd ed., Revised, And ext., - M, Finances and statistics, 1986. 366 p. silt, (Mathematical-static methods abroad).

Bilokon O. Status and prospects of development of disinfection robotic systems. Materials VIII All-Ukrainian scientific-practical conference “V.M. Glushkov reading” 2019.11.29. P. 16–19.


  • There are currently no refbacks.