Abstract
We discuss a random search algorithm with self-learning designed for solving a problem of training of feedforward neural networks and compare it with gradient algorithms for neural network training with regard to criteria of accuracy and computational complexity.
Similar content being viewed by others
REFERENCES
Zhiglyavsky, A.A. and Zhilinskas, A.G., Methods for Finding a Global Extremum, Moscow: Nauka, 1991.
Kostenko, V.A., Multi-start method with cutting for solving problems of unconditional optimization, Opt. Mem. Neural Networks, 2020, vol. 29, no. 1, pp. 30–36.
Rumelhart, D., Hinton, G., and Williams, R., Learning internal reprentations by error propagation, in Parallel Distributed Processing, Cambridge, MA: MIT Press, 1986, vol. 1, pp. 318–362.
Parker, D., Learning logic, Invention Report S81-64, File 1, Office of Technology Licensing, Stanford, CA: Stanford University, 1982.
Werbos, P., Beyond regression: New tools for prediction and analysis in the behavioral sciences, Masters Thesis, Harward Univ., 1974.
Bartsev, S.I. and Okhonin, V.A., Adaptive information processing networks, Preprint of Inst. of Philosophy, Sib. Branch USSR Acad. Sci., Krasnoyarsk, 1986, no. 59B.
Hagan, M. and Menhaj, M., Training feedforward networks with the Marquardt algorithm, IEEE Trans. Neural Networks, 1994, vol. 5, no. 6, pp. 989–993.
Wasserman, F., Neurocomputer Technology, Moscow: Mir, 1992.
Rastrigin, L.A., Statistical Search Methods, Moscow: Nauka, 1968.
MSE. https://en.wikipedia.org/wiki/Mean_squared_error.
Priyesh Patel, Meet Nandu, and Purva Raut, Initialization of weights in neural networks, Int. J. Sci. Eng. Dev. Res., 2018, vol. 3, no. 11, pp. 73–79.
Funding
The work was supported by RBRF grant no. 19-07-00614.
Author information
Authors and Affiliations
Corresponding authors
About this article
Cite this article
Kostenko, V.A., Seleznev, L.E. Random Search Algorithm with Self-Learning for Neural Network Training. Opt. Mem. Neural Networks 30, 180–186 (2021). https://doi.org/10.3103/S1060992X2102003X
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X2102003X