Skip to main content

Table 5 Algorithmic rules for flexible neural tree models

From: A laminar augmented cascading flexible neural forest model for classification of cancer subtypes based on gene expression data

1

The output of the leaf node is the value of a given input feature variable

2

The output of a flexible neuron \(+M\)(non-leaf nodes) can be produced as formula (3) where \(I_j\) is the input to the current node, \(\omega _j\) is the corresponding weight and \(\theta\) is the node’s oset or bias

3

The output of each node is used as the input value of the node to which it is connected at the previous level

4

Calculate the value of the output vector from bottom to top, from leaf node to root node