2000/07/01 by B.D. Calvert, Bruce Calvert, C.A. Marinov +1
Computer Science · Engineering · #Control Systems and Identification #Fuzzy Logic and Control Systems #Neural Networks and Applications
paper · doi:10.1109/72.857764
openalex publication_date 2000/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
An analog Hopfield type neural network is given, that identifies the K largest components of a list of d of N real numbers. The neurons are identical, with a tanh characteristic, and the weight matrix is symmetric and fully filled. The list to be processed is a summand of the input currents of the neurons, and the network is started from zero. We provide easily computable restrictions on the parameters. The main emphasis here is on the magnitude of the neuronal gain. A complete mathematical analysis is given. The trajectories are shown to eventually have positive components precisely in the positions given by the K largest elements in the input list.