Design of neural predictors using tools of chaos theory and Bayesian learning

In this paper a new approach to design efficient neural networks based predictors of noise-free chaotic time series is proposed. Using tools of chaos theory, we can provide helpful indications to appropriately design the architectures of time delay neural networks in a very rapid fashion. After that, by combining an efficient data pre-processing with Bayesian learning, we train neural models that are able to fully capture the dynamics of the underlying systems creating powerful predictors of chaotic time series. We test on several benchmarks the proposed approach achieving results comparable or even better than those of many recurrent neural networks. We also prove that the existing local models lose their well-known advantage when compared to our method, with the benefit of using a much smaller number of parameters.