Exploration of Solving Methods and Applications of Neural Network Models in Optimization Problems


  • Beichen Zhao




Neural network models, Optimization problems, Solution methods, Application exploration


With the booming growth of artificial intelligence (AI) technology, machine learning (ML) as its core component has shown enormous potential and application value in solving optimization problems. Among numerous ML algorithms, neural networks (NN) have become one of the preferred tools for handling optimization problems due to their high flexibility and powerful learning ability. This article focuses on the application of NN in the field of image recognition, exploring its solution methods and application exploration. Image recognition, as an important branch in the field of AI, aims to recognize and understand information in images through computer algorithms. NN can automatically learn features in images and construct complex classification models by simulating the connections and working modes of human brain neurons. By applying the NN model, the performance of the image recognition system has been significantly improved. NN can accurately recognize objects, scenes, and text information in images, providing strong technical support for fields such as intelligent security, autonomous driving, and medical diagnosis. With the continuous progress of technology and the expansion of application scenarios, NN will play an important role in more fields, promoting the rapid growth of AI technology.


Garzón Casado A, Cano Marchal P, Wagner C, et al. Constraint reformulations for set point optimization problems using fuzzy cognitive map models [J]. Optimal Control Applications and Methods, 2022, 43(3): 711-721.

Asha. Deep neural networks-based classification optimization by reducing the feature dimensionality with the variants of gravitational search algorithm [J]. International Journal of Modern Physics C, 2021, 32(10): 2150137.

Diligenskaya A, Samokish A. Parametric identification of technological thermophysics processes based on neural network approach [J]. Journal of Vibroengineering, 2021, 23(6): 1407-1417.

Cao Y, Fan X, Guo Y, et al. Multi-objective optimization of injection-molded plastic parts using entropy weight, random forest, and genetic algorithm methods [J]. Journal of Polymer Engineering, 2020, 40(4):360-371.

Keshavarzzadeh V, Kirby R M, Narayan A. Parametric topology optimization with multiresolution finite element models [J]. International Journal for Numerical Methods in Engineering, 2019, 119(7): 567-589.

Bacanin N, Bezdan T, Al-Turjman F, et al. Artificial flora optimization algorithm with genetically guided operators for feature selection and neural network training [J]. International Journal of Fuzzy Systems, 2022, 24(5): 2538-2559.

Moghaddas M, Tohidi G. An efficient neurodynamic model to solve nonconvex nonlinear optimization problems and its applications [J]. Expert Systems, 2020, 37(3): e12498.

Kheyrinataj F, Nazemi A. Fractional Chebyshev functional link neural network-optimization method for solving delay fractional optimal control problems with Atangana-Baleanu derivative [J]. Optimal Control Applications and Methods, 2020, 41(3): 808-832.

Wang K, Lozano L, Cardonha C, et al. Optimizing over an ensemble of trained neural networks [J]. INFORMS Journal on Computing, 2023, 35(3): 652-674.

Nazemi A, Mortezaee M. A Novel Collaborate Neural Dynamic System Model for Solving a Class of Min-Max Optimization Problems with an Application in Portfolio Management [J]. The Computer journal, 2019, 62(7):1061-1085.







How to Cite

Zhao, B. (2024). Exploration of Solving Methods and Applications of Neural Network Models in Optimization Problems. International Journal of Computer Science and Information Technology, 3(1), 49-54. https://doi.org/10.62051/ijcsit.v3n1.08

Similar Articles

1-10 of 143

You may also start an advanced similarity search for this article.