In this research paper novel real/complex valued recurrent Hopfield Neural Network (RHNN) is proposed. The method of synthesizing the energy landscape of such a network and the experimental investigation of dynamics of Recurrent Hopfield Network is discussed. Parallel modes of operation (other than fully parallel mode) in layered RHNN is proposed. Also, certain potential applications are proposed.
@article{arxiv.1502.02444,
title = {On the Dynamics of a Recurrent Hopfield Network},
author = {Rama Garimella and Berkay Kicanaoglu and Moncef Gabbouj},
journal= {arXiv preprint arXiv:1502.02444},
year = {2015}
}
Comments
6 pages, 6 figures, 1 table, submitted to IJCNN-2015