What's a difference between the neoperceptron and CNN?












2












$begingroup$


What's a difference (in terms of architecture) between the neoperceptron and CNN?



Both ANNs have hidden layers and scanners, as I understood, but many sources subdivide them in two classes.










share|improve this question











$endgroup$

















    2












    $begingroup$


    What's a difference (in terms of architecture) between the neoperceptron and CNN?



    Both ANNs have hidden layers and scanners, as I understood, but many sources subdivide them in two classes.










    share|improve this question











    $endgroup$















      2












      2








      2





      $begingroup$


      What's a difference (in terms of architecture) between the neoperceptron and CNN?



      Both ANNs have hidden layers and scanners, as I understood, but many sources subdivide them in two classes.










      share|improve this question











      $endgroup$




      What's a difference (in terms of architecture) between the neoperceptron and CNN?



      Both ANNs have hidden layers and scanners, as I understood, but many sources subdivide them in two classes.







      neural-network cnn






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited yesterday









      nbro

      290417




      290417










      asked Oct 25 '18 at 23:40









      ШахШах

      1257




      1257






















          1 Answer
          1






          active

          oldest

          votes


















          2












          $begingroup$

          According to the research paper, neoperceptrons are a class of CNN that are not sensitive to rotations.



          One of the issues with traditional kernels (that was the case before CNN and it is still true with them) is that the rotation of the input image would lead to different results, because the neurons in the dense layer would have different levels of activations.



          With these new neurons, you don't get an issue with orientation. So in theory, if you have a gradient in your image, no matter what the orientation is, you would get the same value.



          For a traditional CNN, you would get maximum activation with the original orientation, inverse with a 180° rotated image, and no activation with 90° or 270°.






          share|improve this answer









          $endgroup$













          • $begingroup$
            Thank you very much for explanation! Everything fell into place
            $endgroup$
            – Шах
            Oct 26 '18 at 8:29










          • $begingroup$
            Which research paper are you referring to?
            $endgroup$
            – nbro
            yesterday











          Your Answer





          StackExchange.ifUsing("editor", function () {
          return StackExchange.using("mathjaxEditing", function () {
          StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
          StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
          });
          });
          }, "mathjax-editing");

          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%2f40249%2fwhats-a-difference-between-the-neoperceptron-and-cnn%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









          2












          $begingroup$

          According to the research paper, neoperceptrons are a class of CNN that are not sensitive to rotations.



          One of the issues with traditional kernels (that was the case before CNN and it is still true with them) is that the rotation of the input image would lead to different results, because the neurons in the dense layer would have different levels of activations.



          With these new neurons, you don't get an issue with orientation. So in theory, if you have a gradient in your image, no matter what the orientation is, you would get the same value.



          For a traditional CNN, you would get maximum activation with the original orientation, inverse with a 180° rotated image, and no activation with 90° or 270°.






          share|improve this answer









          $endgroup$













          • $begingroup$
            Thank you very much for explanation! Everything fell into place
            $endgroup$
            – Шах
            Oct 26 '18 at 8:29










          • $begingroup$
            Which research paper are you referring to?
            $endgroup$
            – nbro
            yesterday
















          2












          $begingroup$

          According to the research paper, neoperceptrons are a class of CNN that are not sensitive to rotations.



          One of the issues with traditional kernels (that was the case before CNN and it is still true with them) is that the rotation of the input image would lead to different results, because the neurons in the dense layer would have different levels of activations.



          With these new neurons, you don't get an issue with orientation. So in theory, if you have a gradient in your image, no matter what the orientation is, you would get the same value.



          For a traditional CNN, you would get maximum activation with the original orientation, inverse with a 180° rotated image, and no activation with 90° or 270°.






          share|improve this answer









          $endgroup$













          • $begingroup$
            Thank you very much for explanation! Everything fell into place
            $endgroup$
            – Шах
            Oct 26 '18 at 8:29










          • $begingroup$
            Which research paper are you referring to?
            $endgroup$
            – nbro
            yesterday














          2












          2








          2





          $begingroup$

          According to the research paper, neoperceptrons are a class of CNN that are not sensitive to rotations.



          One of the issues with traditional kernels (that was the case before CNN and it is still true with them) is that the rotation of the input image would lead to different results, because the neurons in the dense layer would have different levels of activations.



          With these new neurons, you don't get an issue with orientation. So in theory, if you have a gradient in your image, no matter what the orientation is, you would get the same value.



          For a traditional CNN, you would get maximum activation with the original orientation, inverse with a 180° rotated image, and no activation with 90° or 270°.






          share|improve this answer









          $endgroup$



          According to the research paper, neoperceptrons are a class of CNN that are not sensitive to rotations.



          One of the issues with traditional kernels (that was the case before CNN and it is still true with them) is that the rotation of the input image would lead to different results, because the neurons in the dense layer would have different levels of activations.



          With these new neurons, you don't get an issue with orientation. So in theory, if you have a gradient in your image, no matter what the orientation is, you would get the same value.



          For a traditional CNN, you would get maximum activation with the original orientation, inverse with a 180° rotated image, and no activation with 90° or 270°.







          share|improve this answer












          share|improve this answer



          share|improve this answer










          answered Oct 26 '18 at 8:24









          Matthieu BrucherMatthieu Brucher

          69113




          69113












          • $begingroup$
            Thank you very much for explanation! Everything fell into place
            $endgroup$
            – Шах
            Oct 26 '18 at 8:29










          • $begingroup$
            Which research paper are you referring to?
            $endgroup$
            – nbro
            yesterday


















          • $begingroup$
            Thank you very much for explanation! Everything fell into place
            $endgroup$
            – Шах
            Oct 26 '18 at 8:29










          • $begingroup$
            Which research paper are you referring to?
            $endgroup$
            – nbro
            yesterday
















          $begingroup$
          Thank you very much for explanation! Everything fell into place
          $endgroup$
          – Шах
          Oct 26 '18 at 8:29




          $begingroup$
          Thank you very much for explanation! Everything fell into place
          $endgroup$
          – Шах
          Oct 26 '18 at 8:29












          $begingroup$
          Which research paper are you referring to?
          $endgroup$
          – nbro
          yesterday




          $begingroup$
          Which research paper are you referring to?
          $endgroup$
          – nbro
          yesterday


















          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%2f40249%2fwhats-a-difference-between-the-neoperceptron-and-cnn%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