Relevance Determination for Learning Vector Quantization Using the Fisher Criterion Score

Two new feature relevance determination algorithms are proposed for learning vector quantization. The algorithms exploit the positioning of the prototype vectors in the input feature space to estimate Fisher criterion scores for the input dimensions during training. These scores are used to form online estimates of weighting factors for an adaptive metric that accounts for dimensional relevance with respect to classifier output. The methods offer theoretical advantages over previously proposed LVQ relevance determination techniques based on gradient descent, as well as performance advantages as demonstrated in experiments on various datasets including a visual dataset from a cognitive robotics object affordance learning experiment.