In multistep prediction with LSTM(keras), say we had this kind of result: target = [[1,2,3] ,[4,5,6] ] predictions = [[1.1,2.2,3.3] , [4.4,5.5,6.6]]

When we choose mean_squared_error as the loss while fitting a model in keras, how exactly is it calculated? I had the intuition that it's done separately for each target(& it's corresponding predictions) , and the results are simply averaged out. I couldn't find an official source for the same.



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.