The data table is Bright Wire's workhorse data type.
Each column has a distinct data type, such as string, number, date or boolean.
Different machine learning algorithms expect data tables with different column types.
The type of each column can be as simple as a single number, and as complex as a 3D tensor (a cube of numbers).
This is expressed with a two column data table - the first column is of type Index List and the second (the classification target) is of type string.
A simple feedforward neural network expects a table with two columns, each of type Vector.
It expects the second column (the classification label) to be of type Vector.
A recurrent neural network expects an input column of type Matrix.
Finally a convolutional neural network expects an input column type of 3DTensor and output column of type Vector.