Global attractivity and forward neural networks
نویسندگان
چکیده
منابع مشابه
Global Convergence for Discrete Dynamical Systems and Forward Neural Networks
Using a theoretical result regarding the global stability of discrete dynamical systems of lower triangular form, we establish convergence properties of forward neural networks when the neuron response functions fail to be continuous.
متن کاملNecessary and Sufficient Conditions for Global Attractivity of Hopfield-type Neural Networks with Time Delays∗
In this paper, two classes of twoand three-dimensional Hopfield-type neural networks with time delays are considered by using a completely different method from known results. Some necessary and sharper sufficient criteria for the global attractivity of the equilibria of the neural networks are present.
متن کاملTopographic mappings and feed-forward neural networks
This copy of the thesis has been supplied on condition that anyone who consults it is understood to recognise that its copyright rests with its author and that no quotation from the thesis and no information derived from it may be published without proper acknowledgement. Thesis Summary This thesis is a study of the generation of topographic mappings — dimension reducing transformations of data...
متن کاملGlobal Solar Radiation Prediction for Makurdi, Nigeria Using Feed Forward Backward Propagation Neural Network
The optimum design of solar energy systems strongly depends on the accuracy of solar radiation data. However, the availability of accurate solar radiation data is undermined by the high cost of measuring equipment or non-functional ones. This study developed a feed-forward backpropagation artificial neural network model for prediction of global solar radiation in Makurdi, Nigeria (7.7322 N lo...
متن کاملEstimating and modeling monthly mean daily global solar radiation on horizontal surfaces using artificial neural networks
In this study, an artificial neural network based model for prediction of solar energy potential in Kerman province in Iran has been developed. Meteorological data of 12 cities for period of 17 years (1997–2013) and solar radiation for five cities around and inside Kerman province from the Iranian Meteorological Office data center were used for the training and testing the network. Meteorologic...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied Mathematics Letters
سال: 1996
ISSN: 0893-9659
DOI: 10.1016/0893-9659(96)00055-9