Neural networks are created when they are required for forecasting. Grid input columns are connected to network input nodes, grid output columns are connected to network output nodes and grid serial columns are connected to both network input and output nodes.

1 . Input nodeInput node

Input node

Input nodes are connected to grid input or serial columns.

2 . Output nodeOutput node

Output node

Output nodes are connected to grid output or serial columns.

3 . Hidden nodeHidden node

Hidden node


Hidden nodes are connected to input, output or serial nodes.

4 . ConnectionsConnections


Layers of nodes are fully connected to the adjacent layer.   A connection can have a positive or negative weight. The line color shows the polarity and the thickness shows the weight value relative to the greatest weight.