STOCHASTIC NEURAL NETWORKS AND THEIR SOLUTIONS TO OPTIMISATION PROBLEMS

Year 2012, Volume: 2 Issue: 3, 293 - 297, 01.12.2012

Ruya Samlı

Abstract

Stochastic neural networks which are a type of recurrent neural networks can be basicly and simply expressed as “the neural networks which are built by introducing random variations into the network”. This randomness comes from one of these usages : applying stochastic transfer functions to network neurons or determining the network weights stochastically. This randomness property makes this type of neural networks an ideal tool for optimisation problems which especially cannot be solved with classical methods, or needs better solurions. In this paper, the properties of stochastic neural networks are investigated and the examples of using this type of neural networks for optimisation problems are given

Keywords

Recurrent neural networks, stochastic neural networks, optimisation

References

• Eugene Wong, “Stochastic Neural Networks”, Algorithmica (1991) 6:466-478. Boltzmann Machine, http://en.wikipedia.org/wiki/Boltzmann_machi ne, 25.03. 2012.
• Ling. H., S. Samarasingle, G.D. Kulasiri, “Modelling Displacement Fields of Wood in Compression Loading Using Stochastic Neural Networks”. Hong Ling, Sandhya Samarasinghe, G.Don Kulasiri, “Modelling Variability in Full-field Displacement Profiles and Poisson Ratio of Wood in Compression Using Stochastic Neural Networks”, Silva Fennica 43(5) research articles, ISSN 0037-5330, 2009.
• D. Rosaci, “Stochastic neural networks for transportation systems modeling”, Applied Artificial Intelligence: An International Journal, 26 Nov 2010.
• Álvaro Costa, Raphael N. Markellos, “Evaluating public transport efficiency with neural network models”, Transportation Research Part C: Emerging Technologies Volume 5, Issue 5, October 1997, Pages 301–
• Biswal, B and Dasgupta, “Stochastic neural B. Yegnanarayana, IEEE Transactions On nonstationary earthquakes”,