Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Continuous transformation learning of translation invariant representations

Perry, Gavin, Rolls, E. T. and Stringer, S. M. 2010. Continuous transformation learning of translation invariant representations. Experimental Brain Research 204 (2) , pp. 255-270. 10.1007/s00221-010-2309-0

Full text not available from this repository.

Abstract

We show that spatial continuity can enable a network to learn translation invariant representations of objects by self-organization in a hierarchical model of cortical processing in the ventral visual system. During ‘continuous transformation learning’, the active synapses from each overlapping transform are associatively modified onto the set of postsynaptic neurons. Because other transforms of the same object overlap with previously learned exemplars, a common set of postsynaptic neurons is activated by the new transforms, and learning of the new active inputs onto the same postsynaptic neurons is facilitated. We show that the transforms must be close for this to occur; that the temporal order of presentation of each transformed image during training is not crucial for learning to occur; that relatively large numbers of transforms can be learned; and that such continuous transformation learning can be usefully combined with temporal trace training.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Psychology
Subjects: B Philosophy. Psychology. Religion > BF Psychology
R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
Uncontrolled Keywords: Object recognition - Continuous transformation - Trace learning - Inferior temporal cortex - Invariant representations
Publisher: Springer
ISSN: 0014-4819
Last Modified: 04 Jun 2017 04:02
URI: http://orca.cf.ac.uk/id/eprint/31514

Citation Data

Cited 8 times in Google Scholar. View in Google Scholar

Cited 13 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item