Keras Loss Function for Multidimensional Regression Problem












5












$begingroup$


I am new to DL and Keras. I am trying to solve a regression problem with multivariate outputs (y shape (?, 2)) using Keras (tensorflow backend). I am having my confusion about how the loss is calculated. I use mean absolute error as the loss function. However, since my target data has 2 dimensions, is the loss value calculated as the reduced mean on all dimensions (a scalar as the result)? I checked the Keras source code, it uses K.mean(..., axis=-1) for MAE calculation. If K.mean is the same to numpy.mean, "axis=-1" should do the column mean (for my case, it should return a tensor with shape (?,2) but not a scalar). If this is the case, how could the loss value be a single number (as outputed in the training process log)?



If the MAE return is indeed a scalar (reduced mean), this gives me another problem. The data from each dimension of my target is not in a same range. A reduced mean would be biased towards the high value dimension. Shall I change my model to a multi-task learning model then?



Thanks a lot for your help on this.



L.










share|improve this question









$endgroup$




bumped to the homepage by Community 4 mins ago


This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.




















    5












    $begingroup$


    I am new to DL and Keras. I am trying to solve a regression problem with multivariate outputs (y shape (?, 2)) using Keras (tensorflow backend). I am having my confusion about how the loss is calculated. I use mean absolute error as the loss function. However, since my target data has 2 dimensions, is the loss value calculated as the reduced mean on all dimensions (a scalar as the result)? I checked the Keras source code, it uses K.mean(..., axis=-1) for MAE calculation. If K.mean is the same to numpy.mean, "axis=-1" should do the column mean (for my case, it should return a tensor with shape (?,2) but not a scalar). If this is the case, how could the loss value be a single number (as outputed in the training process log)?



    If the MAE return is indeed a scalar (reduced mean), this gives me another problem. The data from each dimension of my target is not in a same range. A reduced mean would be biased towards the high value dimension. Shall I change my model to a multi-task learning model then?



    Thanks a lot for your help on this.



    L.










    share|improve this question









    $endgroup$




    bumped to the homepage by Community 4 mins ago


    This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.


















      5












      5








      5


      1



      $begingroup$


      I am new to DL and Keras. I am trying to solve a regression problem with multivariate outputs (y shape (?, 2)) using Keras (tensorflow backend). I am having my confusion about how the loss is calculated. I use mean absolute error as the loss function. However, since my target data has 2 dimensions, is the loss value calculated as the reduced mean on all dimensions (a scalar as the result)? I checked the Keras source code, it uses K.mean(..., axis=-1) for MAE calculation. If K.mean is the same to numpy.mean, "axis=-1" should do the column mean (for my case, it should return a tensor with shape (?,2) but not a scalar). If this is the case, how could the loss value be a single number (as outputed in the training process log)?



      If the MAE return is indeed a scalar (reduced mean), this gives me another problem. The data from each dimension of my target is not in a same range. A reduced mean would be biased towards the high value dimension. Shall I change my model to a multi-task learning model then?



      Thanks a lot for your help on this.



      L.










      share|improve this question









      $endgroup$




      I am new to DL and Keras. I am trying to solve a regression problem with multivariate outputs (y shape (?, 2)) using Keras (tensorflow backend). I am having my confusion about how the loss is calculated. I use mean absolute error as the loss function. However, since my target data has 2 dimensions, is the loss value calculated as the reduced mean on all dimensions (a scalar as the result)? I checked the Keras source code, it uses K.mean(..., axis=-1) for MAE calculation. If K.mean is the same to numpy.mean, "axis=-1" should do the column mean (for my case, it should return a tensor with shape (?,2) but not a scalar). If this is the case, how could the loss value be a single number (as outputed in the training process log)?



      If the MAE return is indeed a scalar (reduced mean), this gives me another problem. The data from each dimension of my target is not in a same range. A reduced mean would be biased towards the high value dimension. Shall I change my model to a multi-task learning model then?



      Thanks a lot for your help on this.



      L.







      keras tensorflow regression






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Apr 19 '18 at 19:37









      Li GuoLi Guo

      261




      261





      bumped to the homepage by Community 4 mins ago


      This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.







      bumped to the homepage by Community 4 mins ago


      This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
























          1 Answer
          1






          active

          oldest

          votes


















          0












          $begingroup$

          I fall on same issue with RMSE which by the way may be a good complementary choice of MAE. Thus in order to measure error prediction on multidimentional output the way i implemented was as follow. Measure the index score per dimension then do the average on all dimensions which gives a single scalar value.
          If your data isn t on same scale, apply a standardization on it. And in order to have same order of magnitude on all your output dimensions you also can divide each column by their corresponding test set standard deviation before applying the mean reduce.






          share|improve this answer











          $endgroup$














            Your Answer








            StackExchange.ready(function() {
            var channelOptions = {
            tags: "".split(" "),
            id: "557"
            };
            initTagRenderer("".split(" "), "".split(" "), channelOptions);

            StackExchange.using("externalEditor", function() {
            // Have to fire editor after snippets, if snippets enabled
            if (StackExchange.settings.snippets.snippetsEnabled) {
            StackExchange.using("snippets", function() {
            createEditor();
            });
            }
            else {
            createEditor();
            }
            });

            function createEditor() {
            StackExchange.prepareEditor({
            heartbeatType: 'answer',
            autoActivateHeartbeat: false,
            convertImagesToLinks: false,
            noModals: true,
            showLowRepImageUploadWarning: true,
            reputationToPostImages: null,
            bindNavPrevention: true,
            postfix: "",
            imageUploader: {
            brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
            contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
            allowUrls: true
            },
            onDemand: true,
            discardSelector: ".discard-answer"
            ,immediatelyShowMarkdownHelp:true
            });


            }
            });














            draft saved

            draft discarded


















            StackExchange.ready(
            function () {
            StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f30537%2fkeras-loss-function-for-multidimensional-regression-problem%23new-answer', 'question_page');
            }
            );

            Post as a guest















            Required, but never shown

























            1 Answer
            1






            active

            oldest

            votes








            1 Answer
            1






            active

            oldest

            votes









            active

            oldest

            votes






            active

            oldest

            votes









            0












            $begingroup$

            I fall on same issue with RMSE which by the way may be a good complementary choice of MAE. Thus in order to measure error prediction on multidimentional output the way i implemented was as follow. Measure the index score per dimension then do the average on all dimensions which gives a single scalar value.
            If your data isn t on same scale, apply a standardization on it. And in order to have same order of magnitude on all your output dimensions you also can divide each column by their corresponding test set standard deviation before applying the mean reduce.






            share|improve this answer











            $endgroup$


















              0












              $begingroup$

              I fall on same issue with RMSE which by the way may be a good complementary choice of MAE. Thus in order to measure error prediction on multidimentional output the way i implemented was as follow. Measure the index score per dimension then do the average on all dimensions which gives a single scalar value.
              If your data isn t on same scale, apply a standardization on it. And in order to have same order of magnitude on all your output dimensions you also can divide each column by their corresponding test set standard deviation before applying the mean reduce.






              share|improve this answer











              $endgroup$
















                0












                0








                0





                $begingroup$

                I fall on same issue with RMSE which by the way may be a good complementary choice of MAE. Thus in order to measure error prediction on multidimentional output the way i implemented was as follow. Measure the index score per dimension then do the average on all dimensions which gives a single scalar value.
                If your data isn t on same scale, apply a standardization on it. And in order to have same order of magnitude on all your output dimensions you also can divide each column by their corresponding test set standard deviation before applying the mean reduce.






                share|improve this answer











                $endgroup$



                I fall on same issue with RMSE which by the way may be a good complementary choice of MAE. Thus in order to measure error prediction on multidimentional output the way i implemented was as follow. Measure the index score per dimension then do the average on all dimensions which gives a single scalar value.
                If your data isn t on same scale, apply a standardization on it. And in order to have same order of magnitude on all your output dimensions you also can divide each column by their corresponding test set standard deviation before applying the mean reduce.







                share|improve this answer














                share|improve this answer



                share|improve this answer








                edited Apr 21 '18 at 5:59

























                answered Apr 21 '18 at 5:53









                KyBeKyBe

                260212




                260212






























                    draft saved

                    draft discarded




















































                    Thanks for contributing an answer to Data Science Stack Exchange!


                    • Please be sure to answer the question. Provide details and share your research!

                    But avoid



                    • Asking for help, clarification, or responding to other answers.

                    • Making statements based on opinion; back them up with references or personal experience.


                    Use MathJax to format equations. MathJax reference.


                    To learn more, see our tips on writing great answers.




                    draft saved


                    draft discarded














                    StackExchange.ready(
                    function () {
                    StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f30537%2fkeras-loss-function-for-multidimensional-regression-problem%23new-answer', 'question_page');
                    }
                    );

                    Post as a guest















                    Required, but never shown





















































                    Required, but never shown














                    Required, but never shown












                    Required, but never shown







                    Required, but never shown

































                    Required, but never shown














                    Required, but never shown












                    Required, but never shown







                    Required, but never shown







                    Popular posts from this blog

                    How to label and detect the document text images

                    Vallis Paradisi

                    Tabula Rosettana