A new competitive learning algorithm for vector quantization based on the neuron winning probability

Neural network competitive learning algorithms are widely used for vector quantization. Some typical competitive learning algorithms have been specially investigated, analyzed and their performances have also been evaluated. A new competitive learning algorithm based on the neuron winning probability is presented for vector quantization. Unlike the traditional competitive learning algorithms where only one neuron will win and learn in each competition, every neuron in the proposed probability sensitive competitive learning algorithm (PSCL) will win to some extent, depending on its winning probability and adjustment of distortion distance to the input vector. The new algorithm is shown to be efficient to overcome the problem of neuron underutilization.