Neural networks for time-series forecasting Day 2

Neural networks can be classified into dynamic and static categories.

Static (feedforward) networks have no feedback elements and contain no delays; the output is calculated directly from the input through feedforward connections.

In dynamic networks, the output depends not only on the current input to the network, but also on the current or previous inputs, outputs, or states of the network.

Dynamic networks can also be divided into two categories: those that have only feedforward connections, and those that have feedback, or recurrent, connections.

References

1. Grace Rumantir, Monash University FIT5167 Lecture Notes, 2012.
2. MATLAB 2011b Help Documentation