I'm working on a time series forecasting task, and, in some specific cases, I don't need perfect accuracy, but the network cannot by any means miss by a lot. So, in detriment of a smaller mean error, I want to have fewer big mistakes.

Any suggestions of loss functions or other methods to solve this issue?

  • $\begingroup$ Off the top of my head, you could have a loss function with a penalty term that penalizes higher individual losses. I don't know exactly how this could be implemented in your case, because I also don't understand how you're currently implementing your loss function and training your neural network. $\endgroup$ – nbro Jun 3 '20 at 22:38

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.