how to decide how many nodes are in the output layer?

[targos]

from the tests, it seems that we have one output node

[jajoe]

I believe (not sure) that the test called 'big case' has two output nodes. Here is the features/labels used :

var trainingSet = [[1, 1], [1, 2], [2, 1], [2, 2], [3, 1], [1, 3], [1, 4], [4, 1],
            [6, 1], [6, 2], [6, 3], [6, 4], [6, 5], [5, 5], [4, 5], [3, 5]];
var predictions = [[1, 0], [1, 0], [1, 0], [1, 0], [1, 0], [1, 0], [1, 0], [1, 0],
            [0, 1], [0, 1], [0, 1], [0, 1], [0, 1], [0, 1], [0, 1], [0, 1]];

But I will add a test case to check that.