Learning to categorize objects using temporal coherence Conferences

abstract

• The invariance of an objects' identity as it transformed over time provides a powerful cue for perceptual learning. We present an unsupervised learning procedure which maximizes the mutual information between the representations adopted by a feed-forward network at consecutive time steps. We demonstrate that the network can learn, entirely unsupervised, to classify an ensemble of several patterns by observing pattern trajectories, even though there are abrupt transitions from one object to another between trajectories. The same learning procedure should be widely applicable to a variety of perceptual learning tasks.

authors

• Becker, Sue

publication date

• 1992

has subject area

• 1701 Psychology (FoR)
• 1702 Cognitive Sciences (FoR)

published in

• Advances in Neural Information Processing Systems  Journal

presented at event

• Neural Information Processing Systems 1992  Conference

start page

• 361

end page

• 368

volume

• 5