A GENERAL MEAN-BASED ITERATIVE WINNER-TAKE-ALL NEURAL-NETWORK

In this paper, a new iterative winner-take-all (WTA) neural network is developed and analyzed. The proposed WTA neural net with one-layer st ructure is established under the concept of the statistical mean. For three typical distributions of initial activations, the convergence be haviors of the existing and the proposed WTA neural nets are evaluated by theoretical analyses and Monte Carlo Simulations. We found that th e suggested WTA neural network on average requires fewer than Log2M it erations to complete a WTA process for the three distributed inputs, w here M is the number of competitors. Furthermore, the fault tolerances of the iterative WTA nets are analyzed and simulated. From the view p oints of convergence speed, hardware complexity, and robustness to the errors, the proposed WTA is suitable for various applications.