Aiming at limitations of memory function of traditional Hopfield neural network

an improved Hopfield neural network is presented based on theoretical knowledge of Hopfield neural network. Through modifying connection relations matrix in learning phase increase memory ability of network. Design a neural network with associative memory function using Matlab as tool

implement recovery of different degree of stained twodimensional code. Recovery results of network before and after improvement are compared and analyzed

and results show that the improved Hopfield neural network is better for the recovery of stained two-dimensional code.