![Sample our Engineering & Technology journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5933/TOC-Subject-Sample-2021-Engineering-Tech.jpg"})
Abstract
We describe a simple neural model for self-organizing feature maps based on elastic interaction between weight vectors of neurons. The model dynamics are deterministic and parallel and relax to an equilibrium configuration. The overall properties of the model depend on the elastic force used. If the force depends on the pth power of the difference of the weight vectors the density of neurons in the equilibrium configuration is given by the (1/p)th power of the signal density.