This work investigates the framework and statistical performance guarantee of composite neural network, which is composed a collection pre-trained non-instantiated network models connected as rooted directed acyclic graph, for solving complicated applications. A model generally well trained, targeted to approximate specific function. The advantages adopting component in composing are two-fold. ...

After more than 30 years of development, China’s stock exchange market has already had a considerable scale. Modeling and forecasting prices is always problem. Based on the data three stocks given in title, this paper analyzes characteristics development trend each stock. foothold chaos theory [1] studies nonlinear dynamic predictability market, finally tests it.

prediction of precipitation is very important. regarding to the non- linear relationships and uncertainty of models, there is no superior and persuasive model among various proposed models to simulate precise precipitation and its amount. wavelet is one of the novel and very effective methods in time series and signals analyzing, that has been considered in the field of hydrology in recent year...