Neural Networks with Python - [Part 8]
In this tutorial we're going to create the recurrent neural network with two layers, which we're going to train on the dataset that we've created.
The dataset is made of waveforms, which are representative of time series data. The type of recurrent net we're using is an Elman RNN.
In neurolab we have the possibility to use activations or activation functions such as the hyperbolic tangent and the linear. And these exactly the ones that we'll use.
After we create the recurrent net, we're going to train on the dataset comprised of waveforms. Ultimately we do some plotting to view and interpret the output; and we also assess the performance of the RNN on new data.
Please see the video below for the full walkthrough:
To stay in touch with me, follow @cristi
Cristi Vlad Self-Experimenter and Author
bun post bafta
This looks like another level of programming...i learnt alot from this.
Very useful and interesting post