Alternatives to backpropagation

Alternatives to backpropagation

Greedy pretraining

Cascade-correlation learning architecture

This is a method for both building and training.

We start with a bare bones network. We then add nodes one by one, training and then fixing their values.

Extreme learning machines

This is an alternative to backprobagation for training a feedforward neural network.

We start with random parameters for each layer \(W_i\).

We have:

\(\hat y=W_2\sigma (W_1 x)\)

Etc.

We calculate:

\(W_2=\sigma(W_1x)^+Y\)

So \(W_1\) is random and not updated.

\(W_2\) is assigned to minimise loss, where \(W_2\) has no activation function.