The Hopfield-like neural network with governed ground state
Leonid B. Litinskii, M. Yu. Malsagov · BMC Neuroscience · 2013
Using a vector u = (u1, ..., up) let us construct a matrix i, j = 1, .., p, i, j = 1, .., p, where δij is the Kronecker delta, ui ∈ R1 and ‖u‖2 = p. We define a Hopfield-like neural network with a connection matrix Jij = (1− 2x)Mij proportional to M = ( Mij ) and threshold Ti = q(1− x)ui proportional to coordinates ui. Real quantities x andq are our free parameters. The dynamics of the network is defined