Interval Methods for Seeking Fixed Points of Recurrent Neural Networks

The paper describes an application of interval methods to train recurrent neural networks and investigate their behavior. The HIBA_USNE multithreaded interval solver for nonlinear systems and algorithmic differentiation using ADHC are used. Using interval methods, we can not only train the network, but precisely localize all stationary points of the network. Preliminary numerical results for continuous Hopfield-like networks are presented.