Neural Network Solution of Single-Delay Differential Equations

Following the ideas of Lagaris et al. (IEEE Trans Neural Netw 9(5):987-1000, 1998), we use Neural Networks to solve approximatively first-order single-delay differential equations and systems. We apply the proposed novel methodology to various problems with constant delay terms and the resulted continuous solutions prove to be very efficient. This is the case not only for nonstiff problems but for equations with stiffness too.