TU Darmstadt / ULB / TUbiblio

An Adaptive Cellular Network for Subspace Extraction

Koeppl, H. (2006):
An Adaptive Cellular Network for Subspace Extraction.
Pacific Grove, CA, USA, IEEE, In: 2006 Fortieth Asilomar Conference on Signals, Systems and Computers, [Online-Edition: http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=417672...],
[Conference or Workshop Item]

Abstract

The work proposes a novel network structure for the least mean square error reconstruction (LMSER) principle to perform principal subspace analysis (PSA). The LMSER principle allows for an efficient parallel and robust implementation of PSA, where each individual processing cell contains a local adaptation algorithm. Instead of the classical feedforward network topology this work introduces a recursive topology. It is also shown that the fully connected two-layered network can be represented by a network of multiple locally connected processing layers. This locally coupled network closely resembles cellular nonlinear networks (CNN) and is very suitable for a VLSI (very-large-scale-integration) implementation.

Item Type: Conference or Workshop Item
Erschienen: 2006
Creators: Koeppl, H.
Title: An Adaptive Cellular Network for Subspace Extraction
Language: English
Abstract:

The work proposes a novel network structure for the least mean square error reconstruction (LMSER) principle to perform principal subspace analysis (PSA). The LMSER principle allows for an efficient parallel and robust implementation of PSA, where each individual processing cell contains a local adaptation algorithm. Instead of the classical feedforward network topology this work introduces a recursive topology. It is also shown that the fully connected two-layered network can be represented by a network of multiple locally connected processing layers. This locally coupled network closely resembles cellular nonlinear networks (CNN) and is very suitable for a VLSI (very-large-scale-integration) implementation.

Place of Publication: Pacific Grove, CA, USA
Publisher: IEEE
Divisions: 18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications > Bioinspired Communication Systems
18 Department of Electrical Engineering and Information Technology
18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications
Event Title: 2006 Fortieth Asilomar Conference on Signals, Systems and Computers
Date Deposited: 04 Apr 2014 12:31
Official URL: http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=417672...
Export:

Optionen (nur für Redakteure)

View Item View Item