Learning control units for invariant recognition

doi:10.1016/S0925-2312(02)00869-X

Learning control units for invariant recognition

2003-06-01

2

PRE

AI

J

Junmei Zhu *

C

Christoph von der Malsburg

DOI：10.1016/S0925-2312(02)00869-X

原文链接

原文求助

摘要

En 中文

A control unit is a group of synapses that are consistent with each other in terms of transformation parameters. We showed previously that these high-order interactions led to very fast dynamic link matching (DLM) for self-organization of mappings between two patterns, as needed in invariant recognition and many other visual tasks. We present here a model to learn from examples control units and the connection between them, by generalized Hebbian plasticity. Examples for learning are consistent mappings formed, for instance, by conventional DLM. Simulation results for ID patterns showed that the learned results resemble those designed by hand, and thus were very encouraging. (C) 2002 Elsevier Science B.V. All rights reserved.

Keyword:

dynamic link matching

invariant recognition

control unit

Hebbian learning

Learning control units for invariant recognition

摘要

期刊

机构

引用论文