We introduce a recurrent network architecture for modelling a general class of dynamical systems. The network is intended for modelling real-world processes in which empirical measurements of the external and state variables are obtained at discrete time points. The model can learn from multiple temporal patterns, which may evolve on different timescales and be sampled at non-uniform time intervals. We demonstrate the application of the model to a synthetic problem in which target data are only provided at the final time step. Despite the sparseness of the training data, the network is able not only to make good predictions at the final time step for temporal processes unseen in training, but also to reproduce the sequence of the state variables at earlier times. Moreover, we show how the network can infer the existence and role of state variables for which no target information is provided. The ability of the model to cope with sparse data is likely to be useful in a number of applications, particularly the modelling of metal forging.
Network: Computation in Neural Systems, 9(4), 533, 1998
210Kb, 17 pages [download paper].