A multiple elastic feature network having N independent sets of M feature specific neurons that respond to the temporal properties of a number of targets. The targets are represented by sets of M feature specific coordinates. Each of the neurons and its coordinates are labeled with a different one of the feature types, and have an associated receptive field and distortion, locking and expectation parameters. A sequence of candidate coordinates, which include the targets' coordinates as well as false or ghost coordinates, is input to the MEFN. Each successive candidate coordinate selects the closest neuron that has the same feature type and whose receptive field includes the candidate coordinates. The coordinates of the selected neuron and the other neurons in its set are adjusted towards the candidate coordinates. The distortion, expectation and locking parameters measure the distortion in the neurons' coordinates, the elapsed time since each neuron was last selected and the changes in the neurons' coordinates, respectively. As the sets of neurons converge towards respective targets, the expectation, distortion and locking parameters are reduced, and hence the receptive fields are reduced, causing the neurons to lock onto and track the targets.