I have three outputs, each with a different unit. I am searching for an error estimator with the help of which I can select the most suitable Neural Network configuration. I will have to compute the training error as well as the testing error.
With one output, any error estimator (like MAPE or RMSE) would have done the job, but I am confused what will be the best suited for this case as I have three different outputs and I need one single number as the error to compare.
Will SSE be a good fit for it?
I think that this article might help you Article Multi-output local Gaussian process regression: Applications...
Multiple output regression could be a good fit for your issue,
Thank you Walid Elhedda Raphael Luiz Koszalka
I will check them out.
Dear Shibaprasad Bhattacharya
I think this paper can help you
Article Novel Feature Selection and Voting Classifier Algorithms for...
Firstly, choose a objective function i.e., a loss function which seeks the three components on your outputs. Check the activations of all the three outputs if all three are not categorical then you can proceed with regression loss functions.
If you're using tensorflow or keras to design your neural networks refer this link :https://www.tensorflow.org/api_docs/python/tf/keras/metrics.
My suggestion is to use a weighted loss function by proving importance to a single output to leverage the required outcome.
I hope it helps.
- Badges
- Science topic
- Similar topics
- Counseling Psychology
- Confusion