Recurrent and feedforward networks for human-computer interaction

The classification, selection and organization of electronic messages (e-mail) is a task that can be supported by an artificial neural network (ANN). The ANNs (simple recurrent networks and feedforward nets) extract relevant information from incoming messages during a training period, learn the reaction to the incoming message, i.e., a sequence of user actions, and use the learned representation for the proposal of user reactions. The results show that (1) simple recurrent nets and feedforward networks can learn a mapping from random input vectors (a coding of an incoming message) to output patterns (sequences of user reactions), (2) both types of networks absorb random noise as part of the input pattern and generalize well, and (3) simple recurrent networks for sequence production, though significantly larger, learn faster than feedforward nets trained on a similar-structured data set.