I'm experimenting with LSTM for time series prediction. The example I'm starting with uses mean squared error for training the network.

I know that other time series forecasting tools use more "sophisticated" metrics for fitting models - and I'm wondering if it is possible to find a similar metric for training LSTM.

Is there any metric for training LSTM or RNN which is equivalent to the AIC or BIC that is used when training ARIMA models?

  • 3
    $\begingroup$ Don't bother while experimenting. Once you get the stable results with Gaussian, maybe you can start lookint at other error metrics. There's no AIC equivalent in loss functions $\endgroup$ – Aksakal Jan 29 '18 at 19:52

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.