Abstract
Chaotic behavior has been observed in a large number of natural phenomena. That way, chaotic systems are attractive research topics involving their modeling, simulation, design, and applications. In particular, chaotic time-series prediction is a hot topic that requires the development of electronic solutions. In this manner, a field-programmable gate array (FPGA) is used herein to implement an artificial neural network (ANN) that is used to predict chaotic signals that are generated by a chaotic oscillator designed in the FPGA as shown in the previous chapter. In addition to the FPGA realization, a deep description on the selection of hidden layers, neurons, activation function, learning rules, training algorithm, and hardware design issues using FPGAs is given. Finally, experimental results are provided for chaotic signals with different MLE values to demonstrate the appropriateness of the ANN to predict chaotic time series.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Tlelo-Cuautle, E., Rangel-Magdaleno, J., De la Fraga, L. (2016). Artificial Neural Networks for Time Series Prediction. In: Engineering Applications of FPGAs. Springer, Cham. https://doi.org/10.1007/978-3-319-34115-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-34115-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-34113-2
Online ISBN: 978-3-319-34115-6
eBook Packages: EngineeringEngineering (R0)