Learning a simple recurrent neural state space model to behave like Chua's double scroll
Johan A. K. Suykens, Joos P. L. Vandewalle · IEEE Transactions on Circuits and Systems I Fundamental Theory and Applications · 1995
The authors present a simple discrete time autonomous neural state space model (recurrent network) that behaves like Chua's double scroll. The model is identified using Narendra's dynamic back propagation procedure. Learning is done in "packets" of increasing time horizon.>