Achieving self-organization by lateral inhibition

A new model based on self-organization by lateral inhibition (SOLI) is proposed for self-organizing networks. This model combines many of the good features of previous models while overcoming many of the drawbacks. Experiments on this new model indicate that SOLI is well suited for unsupervised learning tasks, such clustering, has the potential to preserve topology, and can be used for novelty detection. It is computationally efficient with O (n) time complexity and is not sensitive to the initial network parameters.