Stephan Kirstein, Heiko Wersing, Horst-Michael Groß, Edgar Körner, "A Vector Quantization Approach for Life-Long Learning of Categories", Proceedings of the International Conference on Neural Information Processing (ICONIP), 2008.

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.