Improved Hopfield Networks for Pattern Sequence Recognition

Abstract

This paper presents a novel continuous-time Hopfield-type network which is suitable for temporal sequence recognition. Since it is difficult to implement a desired flow vector field distribution by using conventional matrix encoding scheme, a time-varying Hopfield model (TVHM) is proposed. The weight matrix of the TVHM is constructed in such a way that its auto-correlation and cross-correlation parts are encoded from two different sets of patterns. The proposed approach is different from the existing methods because neither synchronous dynamics nor interpolated training patterns are required. Experimental results are presented to illustrate the validity, recall capability, and the applications of the proposed model.