Week 11 - Training LSTM-4 for modeled samples
To try to improve the latest results obtained with the recurrent network, I have tried two different ways: increase of neurons and increase of layers
Increase the number of neurons
The increase in neurons is done by doubling this value, the network goes from having 25 neurons to 50. This new network is trained and tested with the dataset that produced the worst results in the simplest structure.
- Sinusoidal dataset, 4 DOF, 80000 training samples, 10000 test samples
รง
The results obtained are better than those of the 25-neuron LSTM, but a good predictive capacity is still not obtained wuith this dataset.
Increase the number of layers
For the number of layers I have done a study gradually increasing the number of LSTM layers in the network.
- Sinusoidal dataset, 4 DOF, 80000 training samples, 10000 test samples
Very good results are obtained that improve until reaching 4 layers, from there the curve rises again. This fact causes the new structure to be defined with 4 layers since it offers the minimum of relative error.
Proposed net
after the results obtained the new defined network is as follows:
Linear dataset results
- 2 DOF, 80000 training samples, 10000 test samples
Parabolic dataset results
Sinusoidal dataset results
- 4 DOF, 80000 training samples, 10000 test samples
Combined dataset results
By getting good results in each type of movement separately we have created a new combined dataset that uses 33% of linear examples, another 33% of parabolic and 34% of sinusoidal.
- Combined 33%-33%-34%, 80000 training samples, 10000 test samples
Conclusions
With the new more complex structure, very good prediction results are achieved, dominating all dynamics in all their DOFs. This fact shows that a more complex structure, in its proper measure, can make the network better predict.