Step 4. Hidden neurons
h
1
, h
2
sums the weighted input
values: net(h
k
) =
𝑤
𝑜𝑘
+ ∑
𝑥
𝑖
𝑛
𝑖=1
∗ 𝑤
𝑖𝑗
applies the
activation function:
𝜑(𝑛𝑒𝑡) =1/(1+𝑒𝑥𝑝
−𝛼∗𝑛𝑒𝑡
) (5)
Then sends the result (in the range 0-1) to the
output layer neurons. In our case, the only output neuron.
Step 5. The output neuron, using formula (3), sums the
weighted input values, and applies the activation function
to calculate the output value.
Then the error is propagated backwards.
Step 6. The output neuron receives the target value —
the output value that is correct for this input signal, and
calculates the error, as well as calculates the amount by
which the weight of the connection will change. In
addition, it calculates the value of the offset adjustment:
and sends it to the neurons in the previous layer.
Step 7. Each hidden neuron sums up the incoming
errors ( from the neurons in the subsequent layer ) and
calculates the error value by multiplying the resulting
value by the derivative of the activation function, as well
as calculates the amount by which the link weight will
change: In addition, it calculates the amount of offset
correction.
Step 8. Each output neuron changes the weights of its
connections to the bias element and the hidden neurons.
Each hidden neuron changes the weights of its
connections to the offset element and the output neuron
Step 9. Checking the termination condition of the
algorithm.
The result of training the neural network and the graph
of the above algorithm is shown in Figure 3-4.
Fig. 3. The values of the weight coefficients of the neural network.
Fig. 4. Graph of weighted and target values of expert assessments.
REFERENCES
[1] А. А. Барсегян, М. С. Куприянов, И. И. Холод, Т. М.Д.,
and С. И. Елизаров, Анализ данных и процессов: учеб.
пособие. 3-е изд., перераб. и доп. — СПб.: БХВ-
Петербург, 2009. — 512 с.: ил. + CD-ROM — (Учебная
литература для вузов). .
[2] Барсегян А.А., Куприянов М.С., Степаненко В.В., Холод
И.И. Технологии анализа данных: Data Mining, Visual
Mining, Text Mining, OLAP. 2-е издание. Санкт–
Петербург, «БХВ-Петербург», 2007. -375 с. .
[3] О.К.Хужаев,
Н.А.Саидрасулов, Ш.Н.Эгамбердиев,
“Синфларга ажратиш масаласини ечишда самарали
усулни танлаш алгоритми. Ахборот коммуникациялар:
тармоқлар, технологиялар, ечимлар”. Ташкент 2019-
№1(49). –с. 39-44.
[4] Искусственные Нейронные Сети и их приложения: учеб.
пособие / Ф.М. Гафаров, А.Ф. Галимянов. – Казань: Изд-
во Казан. ун-та, 2018. – 121 с.
[5] Головина А.Н., “Технология принятия и реализации
управленческих
решений
в
органах
местного
самоуправления. Пути устранения недостатков.,” АЛЛЕЯ
НАУКИ
Издательство
ИП
Шелистов
Денис
Александрович (Издательский центр “Quantum”), vol. 1,
no. 17, 2018.
[6] K. J. Rakhimboev, M. A. Ismailov, and O. U. Khalmuratov,
“Parametric method for evaluation the state of complex
organizational objects,” IOP Conf. Ser. Mater. Sci. Eng., vol.
919, no. 5, 2020, doi: 10.1088/1757-899X/919/5/052043.
[7] В. В. Борисов, В. В. Круглов., “Искусственные
нейронные сети. Теория и практика / 2-е изд. – М. :
Горячая линия–Телеком, 2002. – 382 с. – ISBN: 5-93517-
031-0.”
[8] D. E. Rumelhart, G. E. Hinton, R. J. Williams “Learning
internal representations by error propagation. Parallel
distributed processing. – Vol. 1. – Cambridge, MA: MIT
Press. – pр. 318–362.”
[9] А. О. Т. Нишанов А.Х., Хўжаев О.Қ., “Классификация
масалаларини ечишда нейрон тўри архитектураси ва
ўқитиш алгоритмларини танлаш //Узб.журнал «ТАТУ
Хабарлари». – Ташкент, 2012. – №1. – С. 14-18.”
[10] Kamilov, M. M., et al. "The Method of Applying the
Algorithm of Calculating Grades for Finding Similar
Diagnostics in Medical Information Systems." International
Journal of Innovative Technology and Exploring Engineering,
vol. 8, no. 6, 2019, pp. 722-724. SCOPUS, www.scopus.com.
[11] Urazmatov, T. Q., Nurmetova, B. B., & Kuzibayev, X. S.
(2020). Analysis of big data processing technologies. Paper
presented at the IOP Conference Series: Materials Science
and
Engineering, ,
862(4)
doi:10.1088/1757-
899X/862/4/042006 Retrieved from www.scopus.com
[12] Bahodir, M., & Bahrombek, S. (2019). Information, analysis
ximmingning four neurons chemical name of the information
in intellectual evidence. International Journal of Innovative
Technology and Exploring Engineering, 8(11), 3382-3384.
doi:10.35940/ijitee.J9176.0981119