 Neural NetworksStephen Lynch
Chapter Chapter 20 in Dynamical Systems with Applications using Python, 2018, pp 519-555 from Springer Abstract: Abstract Neural networks are being used to solve all kinds of problems from a wide range of disciplines. Some neural networks work better than others on specific problems and the models are run using continuous, discrete, and stochastic methods. For more information on stochastic methods stochastic methods , the reader is directed to the textbooks at the end of this chapter. The topic is highly interdisciplinary in nature, and so it is extremely difficult to develop an introductory and comprehensive treatise on the subject in one short chapter of a textbook. A brief historical introduction is given in Section 20.1 and the fundamentals are reviewed. Real-world applications are then discussed. The author has decided to concentrate on three types of neural network—the feedforward multilayer network and backpropagation of errors using the generalized delta learning rule, the recurrent Hopfield neural network, and the minimal chaotic neuromodule. The first network is probably the most widely used in applications in the real world; the second is a much studied network in terms of stability and Lyapunov functions; and the third provides a useful introduction to neurodynamics. Date: 2018 There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it. Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-319-78145-7_20 Ordering information: This item can be ordered from DOI: 10.1007/978-3-319-78145-7_20 Access Statistics for this chapter More chapters in Springer Books from Springer |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.