LSTM time series hyperparameter optimization using bayesian optimization
93 views (last 30 days)
Show older comments
anurag kulshrestha on 22 Apr 2019
Answered: Jorge Calvo on 5 Oct 2021
I am working with time series regression problem. I want to optimize the hyperparamters of LSTM using bayesian optimization. I have 3 input variables and 1 output variable.
I want to optimize the number of hidden layers, number of hidden units, mini batch size, L2 regularization and initial learning rate . Code is given below:
numFeatures = 3;
numHiddenUnits = 120;
numResponses = 1;
layers = [ ...
options = trainingOptions('adam', ...
net = trainNetwork(XTrain,YTrain,layers,options);
YPredicted = predict(net,Xval, 'MiniBatchSize',1);
valError = 1 - mean(YPredicted == Yval);
Thanks in advance.
Jorge Calvo on 5 Oct 2021
I thought you would like to know that, in R2021b, we are included an example for training long short-term memory (LSTM) networks using Bayesian optimization in Experiment Manager:
I hope you find it helpful!
Don Mathis on 10 May 2019
Here's an example using a convolutional network instead of an LSTM network. Your LSTM case should look very similar: https://www.mathworks.com/help/deeplearning/examples/deep-learning-using-bayesian-optimization.html
Sinan Islam on 8 May 2021
LSTM is different from CNN. It is obvious that this example is in great demand. Why not Matlab make a proper example dedicated for optimizing LSTM?
If you have R2020b or later, you can use the Experiment Manager app to run Bayesian optimization to determine the best combination of hyperparameters. For more information, see https://www.mathworks.com/help/deeplearning/ug/experiment-using-bayesian-optimization.html.
Each time you run an experiment, the Experiment Manager will find the best combination of hyperparameters for a given setup. To specify what you mean by best, you can select from some standard objective metrics (including validation accuracy, which I think is what the original question was using) or you can define your own.
If you want to do find the best combo of hyperparameters for each of 200 data sets, then you would:
- Setup the experiment for the first data set.
- Run the experiment.
- Modify the setup function to load the next data set.
- Run the experiment again.
- Repeat steps 3 and 4.
This amounts to running 200 different experiments. On the bright side, unless your objective function depends on the data set, you would not need to recode it.
Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!