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
Other ID | JA57ZF49TT |
---|---|
Journal Section | Articles |
Authors | |
Publication Date | December 1, 2012 |
Published in Issue | Year 2012 Volume: 2 Issue: 3 |