Abstract
This paper mainly studies evolutionary operations of interneuron synaptic structure search based on the developed structure synthesis algorithm for feed-forward multilayer network trained with a teacher. The decomposition of neural network learning tasks into a series of subtasks is proposed. During evolutionary search the neural network is not converted to a genotype and all the transformations of synaptic structures are performed directly. This differs from a classical approach to genetic algorithms involving coding phenotype of individuals (structure) to genotype (code string).
Similar content being viewed by others
REFERENCES
Darwin, C., The Origin of Species, London: Murray, 1859.
Holland, J.H., Genetic algorithms, Sci. Am., 1992, vol. 267, no. 1, pp. 66–73.
Khomich, A.V. and Stepanyan, I.V., Karpishuk blocking principle in evolutionary optimization neural network structures, Neurocomput.: Dev. Appl., 2006, no. 3, p. 17.
Yurong Liu, et al., Exponential stability of Markovian jumping Cohen-Grossberg neural networks with mixed mode-dependent time-delays, Neurocomputing, 2016, vol. 177, p. 409.
Bing Xu, Naiya Wang, Tianqi Chen, and Mu Li, Empirical Evaluation of Rectified Activations in Convolutional Network, 2015. arXiv:1505.00853 [cs.LG]
Schmidhuber, J., Deep learning in neural networks: An overview, Neural Networks, 2015, vol. 61, pp. 85–117. https://doi.org/10.1016/j.neunet.2014.09.003
Goodfellow, I., Bengio, Y., and Courville, A., Deep Learning, MIT Press, 2016.
Cauchy, A.L., Sur les formules qui résultent de l’emploie du signe et sur > ou <, et sur les moyennes entre plusieurs quantités, in Cours d’Analyse de l’École Royale Polytechnique; I.re Partie. Analyse Algébrique, 1821, pp. 373–377.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Stepanyan, I.V. Evolutionary Operations of Interneuron Synaptic Structure for Feed-Forward Multilayer Networks. J. Mach. Manuf. Reliab. 49, 874–877 (2020). https://doi.org/10.3103/S105261882010009X
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S105261882010009X