A Vector Quantization Approach for Life-Long Learning of Categories

13 years 5 months ago

Download www.tu-ilmenau.de

We present a category learning vector quantization (cLVQ) approach for incremental and life-long learning of multiple visual categories where we focus on approaching the stability-plasticity dilemma. To achieve the life-long learning ability an incremental learning vector quantization approach is combined with a category-specific feature selection method in a novel way to allow several metrical "views" on the representation space for the same cLVQ nodes.

Stephan Kirstein, Heiko Wersing, Horst-Michael Gro

Real-time Traffic

ICONIP 2008 | Incremental Learning Vector | Information Technology | Learning Vector Quantization | Life-long Learning |

claim paper

» Comparison of relevance learning vector quantization with other metric adaptive classifica...

» Rapid Online Learning of Objects in a Biologically Motivated Recognition Architecture

» Performance analysis of LVQ algorithms A statistical physics approach

» Generalized matrix learning vector quantizer for the analysis of spectral data

» Constrained Learning Vector Quantization or Relaxed kSeparability

» Extensions of vector quantization for incremental clustering

» Automatic Categorization of Image Regions Using Dominant Color Based Vector Quantization

» Statistical Mechanics of Online Learning

Post Info
More Details (n/a)

Added	29 Oct 2010
Updated	29 Oct 2010
Type	Conference
Year	2008
Where	ICONIP
Authors	Stephan Kirstein, Heiko Wersing, Horst-Michael Gross, Edgar Körner

Comments (0)

Sciweavers

A Vector Quantization Approach for Life-Long Learning of Categories

ICONIP 2008 | Incremental Learning Vector | Information Technology | Learning Vector Quantization | Life-long Learning |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers