hintonwb (Neural Network Toolbox)

Hinton graph of weight matrix and bias vector

hintonwb(W,b,maxw,minw)

Description

hintonwb(W,B,maxw,minw) takes these inputs,

W - S x R weight matrix.

B - S x 1 bias vector.

maxw - Maximum weight, default = max(max(abs(W))).

minw - Minimum weight, default = M1/100.

and displays a weight matrix and a bias vector represented as a grid of squares.

Each square's area represents a weight's magnitude. Each square's projection (color) represents a weight's sign; inset (red) for negative weights, projecting (green) for positive. The weights are shown on the left.

Examples

The following code produces the result shown below.

W = rands(4,5);
b = rands(4,1);
hintonwb(W,b)