A Vector Quantization Approach for Life-Long Learning of Categories

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.

• Type: Conference
• Year: 2008
• Where: ICONIP
• Authors: Stephan Kirstein, Heiko Wersing, Horst-Michael Gross, Edgar Körner
• Keywords: ICONIP 2008, Incremental Learning Vector, Information Technology, Learning Vector Quantization, Life-long Learning