maxlinlr (Neural Network Toolbox)

Maximum learning rate for a linear layer

lr = maxlinlr(P)
lr = maxlinlr(P,'bias')

maxlinlr is used to calculate learning rates for newlin.

maxlinlr(P) takes one argument,

P - R x Q matrix of input vectors.

and returns the maximum learning rate for a linear layer without a bias that is to be trained only on the vectors in P.

maxlinlr(P,'bias') returns the maximum learning rate for a linear layer with a bias.

Examples

Here we define a batch of 4 2-element input vectors and find the maximum learning rate for a linear layer with a bias.

P = [1 2 -4 7; 0.1 3 10 6];
lr = maxlinlr(P,'bias')