Machine Learning of Dynamical Systems Lecture 2: Learning ARX models using Keras (TensorFlow)

#machinelearning #machinelearningbasics #pythonprogramming #timeseries #timeseriesanalysis
It takes a significant amount of time and energy to create these free video tutorials. You can support my efforts by making a PayPal donation or by becoming a Patreon:

A detailed post accompanying this video (with codes) can be found here:
In this lecture, we demonstrate how to estimate an AutoRegressive with eXogenous (ARX) models of dynamical systems and time series using machine learning techniques. We use Keras (TensorFlow) machine learning library and the Python programing language.

[aleksandarhaber]

It takes a significant amount of time and energy to create these free video tutorials. You can support my efforts by making a PayPal donation or by becoming a Patreon:

[aleksandarhaber]

A detailed post accompanying this video (with codes) can be found here:

[VR-fhim]

Very nice explanation and good notes. Thanks.

[ceciliacecilia]

Thank you for the explanation, I want to ask, If I have more than one set of time series, how should I reshape my data?

[kuepper]

Thanks for the video! Can you tell me if I can import the ARX model into Matlab? I have trained an artificial neural network in Keras and would like to use it in Matlab as an ARX model. However, I am having a hard time importing it within Matlab.

[mazenezzeddine]

Thank you Aleksander, very clear, do you have a video about about NARX (non linear ARX)? any hint on real-time continous/online learning ARX()?

[MrCuan]

Hey thank you very much for this informative lecture. I have had a look at your videos and cant find the first lecture or the next in the series. If they are not uploaded could you help me out with any other resources on this topic?

[tuanazzam]

It is a nice explaination, But I couldn't find the backward euler code (from backward_euler import simulate) and the lecture series related with this lecture. Thank you