Performance analysis of locally recurrent neural networks

Many practical applications of neural networks require the identification o f nonlinear deterministic systems or chaotic systems. In these cases the us e of a network architecture known as locally recurrent neural network (LRNN ) is often preferable in place of standard feedforward multi-layer perceptr on (MLP) networks, or of globally recurrent neural network. In this paper l ocally recurrent networks are used to simulate the behaviour of the Chua's circuit that can be considered a paradigm for studying chaos. It is shown t hat such networks are able to identify the underlying link among the state variables of the Chua's circuit. Moreover, they are able to behave like an autonomous Chua's double scroll, showing a chaotic behaviour of the state v ariables obtainable through a suitable circuit elements choice.