- It is set of connected i/o units in which each connection has a weight associated with it.
- During the learning phase the network learns by adjusting the weights so as to be able to predict the correct class label of i/p labels.
- It also referred as connectionist learning due to connection between units.
- It has long training time and poor interpretability but has tolerance to noisy data.
- It can classify pattern on which they have not been trained.
- Well suited for continuous valued i/ps.
- It has parallel topology and processing.
- Before training the network topology must be designed by:
- Specifying number of i/p nodes/units: Depends upon number of independent variable in data set.
- Number of hidden layers: Generally only layer is considered in most of the Two layers can be designed for complex problem. Number of nodes in the hidden layer can be adjusted iteratively.
- Number of output nodes/units: Depends upon number of class labels of the data
- Learning rate: Can be adjusted iteratively.
- Learning algorithm: Any appropriate learning algorithm can be selected during training phase.
- Bias value: Can be adjusted iteratively.
- During training the connection weights must be adjusted to fit i/p values with the o/p values.
