Toward Optimal Synthesis of Discrete-Time Hopfield Neural Network
Garimella Rama Murthy · IEEE Transactions on Neural Networks and Learning Systems · 2022
In this research brief, the relationship between eigenvectors (with {+1, -1} components) of a synaptic weight matrix W and the stable/anti-stable states of discrete-time Hopfield associative memory (HAM) is established. Also, the synthesis of W with desired stable/anti-stable states using spectral representation of W in even/odd dimension is discussed when the threshold vector is a non-zero vector. Freedom in choice of eigenvalues is capitalized to improve the noise immunity of the Hopfield neural network (HNN). Also, the problem of optimal synthesis of Hopfield Associative memory is formulated.