A neural net was trained with backpropagation to identify users in a multi-user unix system, based on the shell commands they used during a login session. The trained network recognized unusual activity reliably, suggesting that user profiles is a good way to detect novel attacks.
An SRN network was trained to predict the measurements of a dynamical system. After training, the output of the SRN could be used to rectify noise in the measurements. Importantly, such rectification is possible without explicit knowledge of the system dynamics.