4.Association. A neural network can be trained to “remember” a number of unique patterns so that when a distorted version of a particular pattern is presented the network associates it with the closest one in is memory and returns the original version of that particular pattern.
This can be useful for restoring noisy or incomplete. Type of ANN used for this task include Hopfield networks.
ANN have been applied in many domains. A survey of their applications in finance can be found in Wallace(2008)and Fadlalla and in Lin(2001).
Many attempts have been made to use neural network to predict and understand financial markets.