Gradient Descent in ReLU Neural Network












0












$begingroup$


I’m new to machine learning and recently facing a problem on back propagation of training a neural network using ReLU activation function shown in the figure. My problem is to update the weights matrices in the hidden and output layers.



The cost function is given as:



$J(Theta) = sumlimits_{i=1}^2 frac{1}{2} left(a_i^{(3)} - y_iright)^2$



where $y_i$ is the $i$-th output from output layer.



enter image description here



Using the gradient descent algorithm, the weights matrices can be updated by:



$Theta_{jk}^{(2)} := Theta_{jk}^{(2)} - alphafrac{partial J(Theta)}{partial Theta_{jk}^{(2)}}$



$Theta_{ij}^{(3)} := Theta_{ij}^{(3)} - alphafrac{partial J(Theta)}{partial Theta_{ij}^{(3)}}$



I understand how to update the weight matrix at output layer $Theta_{ij}^{(3)}$, however I don’t know how to update that from the input layer to hidden layer $Theta_{jk}^{(2)}$ involving the ReLU activation units, i.e. not understanding how to get $frac{partial J(Theta)}{partial Theta_{jk}^{(2)}}$.



Can anyone help me understand how to derive the gradient on the cost function...?









share







New contributor




null is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.







$endgroup$

















    0












    $begingroup$


    I’m new to machine learning and recently facing a problem on back propagation of training a neural network using ReLU activation function shown in the figure. My problem is to update the weights matrices in the hidden and output layers.



    The cost function is given as:



    $J(Theta) = sumlimits_{i=1}^2 frac{1}{2} left(a_i^{(3)} - y_iright)^2$



    where $y_i$ is the $i$-th output from output layer.



    enter image description here



    Using the gradient descent algorithm, the weights matrices can be updated by:



    $Theta_{jk}^{(2)} := Theta_{jk}^{(2)} - alphafrac{partial J(Theta)}{partial Theta_{jk}^{(2)}}$



    $Theta_{ij}^{(3)} := Theta_{ij}^{(3)} - alphafrac{partial J(Theta)}{partial Theta_{ij}^{(3)}}$



    I understand how to update the weight matrix at output layer $Theta_{ij}^{(3)}$, however I don’t know how to update that from the input layer to hidden layer $Theta_{jk}^{(2)}$ involving the ReLU activation units, i.e. not understanding how to get $frac{partial J(Theta)}{partial Theta_{jk}^{(2)}}$.



    Can anyone help me understand how to derive the gradient on the cost function...?









    share







    New contributor




    null is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.







    $endgroup$















      0












      0








      0





      $begingroup$


      I’m new to machine learning and recently facing a problem on back propagation of training a neural network using ReLU activation function shown in the figure. My problem is to update the weights matrices in the hidden and output layers.



      The cost function is given as:



      $J(Theta) = sumlimits_{i=1}^2 frac{1}{2} left(a_i^{(3)} - y_iright)^2$



      where $y_i$ is the $i$-th output from output layer.



      enter image description here



      Using the gradient descent algorithm, the weights matrices can be updated by:



      $Theta_{jk}^{(2)} := Theta_{jk}^{(2)} - alphafrac{partial J(Theta)}{partial Theta_{jk}^{(2)}}$



      $Theta_{ij}^{(3)} := Theta_{ij}^{(3)} - alphafrac{partial J(Theta)}{partial Theta_{ij}^{(3)}}$



      I understand how to update the weight matrix at output layer $Theta_{ij}^{(3)}$, however I don’t know how to update that from the input layer to hidden layer $Theta_{jk}^{(2)}$ involving the ReLU activation units, i.e. not understanding how to get $frac{partial J(Theta)}{partial Theta_{jk}^{(2)}}$.



      Can anyone help me understand how to derive the gradient on the cost function...?









      share







      New contributor




      null is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.







      $endgroup$




      I’m new to machine learning and recently facing a problem on back propagation of training a neural network using ReLU activation function shown in the figure. My problem is to update the weights matrices in the hidden and output layers.



      The cost function is given as:



      $J(Theta) = sumlimits_{i=1}^2 frac{1}{2} left(a_i^{(3)} - y_iright)^2$



      where $y_i$ is the $i$-th output from output layer.



      enter image description here



      Using the gradient descent algorithm, the weights matrices can be updated by:



      $Theta_{jk}^{(2)} := Theta_{jk}^{(2)} - alphafrac{partial J(Theta)}{partial Theta_{jk}^{(2)}}$



      $Theta_{ij}^{(3)} := Theta_{ij}^{(3)} - alphafrac{partial J(Theta)}{partial Theta_{ij}^{(3)}}$



      I understand how to update the weight matrix at output layer $Theta_{ij}^{(3)}$, however I don’t know how to update that from the input layer to hidden layer $Theta_{jk}^{(2)}$ involving the ReLU activation units, i.e. not understanding how to get $frac{partial J(Theta)}{partial Theta_{jk}^{(2)}}$.



      Can anyone help me understand how to derive the gradient on the cost function...?







      neural-network gradient-descent activation-function





      share







      New contributor




      null is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.










      share







      New contributor




      null is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.








      share



      share






      New contributor




      null is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked 4 mins ago









      nullnull

      1




      1




      New contributor




      null is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      null is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      null is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






















          0






          active

          oldest

          votes












          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
          });


          }
          });






          null is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f49666%2fgradient-descent-in-relu-neural-network%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes








          null is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          null is a new contributor. Be nice, and check out our Code of Conduct.













          null is a new contributor. Be nice, and check out our Code of Conduct.












          null is a new contributor. Be nice, and check out our Code of Conduct.
















          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%2f49666%2fgradient-descent-in-relu-neural-network%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