|
Neural networks are used in many different applications because of their ability to generalize and describe
non-linear processes. The following sections covers some aspects of what neural networks are used for.
Pattern association: There are two types of pattern association, autoassociation and heteroassociation.
Autoassociation is about constantly showing the network a certain pattern, the network should be able to store
this pattern, and then when a distorted image of the same pattern shows up, the task is to retrieve the pattern.
Heteroassociation is different in the sense that it is supervised, and it is a pairing of a set of input patterns and a set
of output patterns. Mostly it is about the retrieving phase, xk is a key pattern and yk is a memorised pattern, the task is to
make the network retrieve yk at the presentation of xk.
|
