## Very simple self-connected linear unit called the error carousel.

## Constant error flow: e(t) = f’(net(t)) w e(t+1) = 1.0

## Most natural: f linear, w = 1.0 fixed.

## Purpose: Just deliver errors, leave learning to other weights.

Previous slide | Next slide | Back to first slide | View graphic version |

Back to J. Schmidhuber's Recurrent neural network page