Regularization: global or layerwise?












0












$begingroup$


Keras gives you the option to apply regularization differently to different layers. I mean, why not? Though when I first learned about neural nets (from ESL), I thought of it as a global parameter.



Global is simpler to tune, but obviously a global penalty can be no better than equally efficient when compared to some optimal set of layerwise ones.



So, what are the cases where different penalties for different layers will work better than a single global penalty, and better-enough to be worth the bother?






machine-learning neural-network keras regularization







share|improve this question









$endgroup$

















    0












    $begingroup$


    Keras gives you the option to apply regularization differently to different layers. I mean, why not? Though when I first learned about neural nets (from ESL), I thought of it as a global parameter.



    Global is simpler to tune, but obviously a global penalty can be no better than equally efficient when compared to some optimal set of layerwise ones.



    So, what are the cases where different penalties for different layers will work better than a single global penalty, and better-enough to be worth the bother?






    machine-learning neural-network keras regularization







    share|improve this question









    $endgroup$















      0












      0








      0





      $begingroup$


      Keras gives you the option to apply regularization differently to different layers. I mean, why not? Though when I first learned about neural nets (from ESL), I thought of it as a global parameter.



      Global is simpler to tune, but obviously a global penalty can be no better than equally efficient when compared to some optimal set of layerwise ones.



      So, what are the cases where different penalties for different layers will work better than a single global penalty, and better-enough to be worth the bother?






      machine-learning neural-network keras regularization







      share|improve this question









      $endgroup$




      Keras gives you the option to apply regularization differently to different layers. I mean, why not? Though when I first learned about neural nets (from ESL), I thought of it as a global parameter.



      Global is simpler to tune, but obviously a global penalty can be no better than equally efficient when compared to some optimal set of layerwise ones.



      So, what are the cases where different penalties for different layers will work better than a single global penalty, and better-enough to be worth the bother?






      machine-learning neural-network keras regularization




      machine-learning neural-network keras regularization






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked 1 hour ago









      generic_usergeneric_user

      29418




      29418






















          1 Answer
          1






          active

          oldest

          votes


















          0












          $begingroup$

          Regularisation is a technique to solve overfitting.



          This feature from Keras is going to help a lot in many scenarios. Few times we don't want simpler but a granulr tuning.




          1. CNN: we all know that each convolution layer can contribute to certain set of features from the dataset, and we now a days know what it is trying to do, by defining regularisation to each layer differently, we can better understand how each layer is effecting the final output

          2. Transfer Learning: Where we want learn from the already trained network, and use that domain knowledge. now during this, we can now control, how much we want to regularise before/after merging from the base network.

          3. Multi Task Learning: This is a technique in which we learn multiple tasks together, now with this kind of regularisation we can now control before the merge of the layers, how much of the information can be merged.


          these are the quick things i could think of. But there are definitely lots of other uses.



          Vote up, if this helps ;)





          share









          $endgroup$













          • $begingroup$
            Are you a neural network? You're not wrong but that totally doesn't answer my question.
            $endgroup$
            – generic_user
            21 secs ago












          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%2f48384%2fregularization-global-or-layerwise%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












          $begingroup$

          Regularisation is a technique to solve overfitting.



          This feature from Keras is going to help a lot in many scenarios. Few times we don't want simpler but a granulr tuning.




          1. CNN: we all know that each convolution layer can contribute to certain set of features from the dataset, and we now a days know what it is trying to do, by defining regularisation to each layer differently, we can better understand how each layer is effecting the final output

          2. Transfer Learning: Where we want learn from the already trained network, and use that domain knowledge. now during this, we can now control, how much we want to regularise before/after merging from the base network.

          3. Multi Task Learning: This is a technique in which we learn multiple tasks together, now with this kind of regularisation we can now control before the merge of the layers, how much of the information can be merged.


          these are the quick things i could think of. But there are definitely lots of other uses.



          Vote up, if this helps ;)





          share









          $endgroup$













          • $begingroup$
            Are you a neural network? You're not wrong but that totally doesn't answer my question.
            $endgroup$
            – generic_user
            21 secs ago
















          0












          $begingroup$

          Regularisation is a technique to solve overfitting.



          This feature from Keras is going to help a lot in many scenarios. Few times we don't want simpler but a granulr tuning.




          1. CNN: we all know that each convolution layer can contribute to certain set of features from the dataset, and we now a days know what it is trying to do, by defining regularisation to each layer differently, we can better understand how each layer is effecting the final output

          2. Transfer Learning: Where we want learn from the already trained network, and use that domain knowledge. now during this, we can now control, how much we want to regularise before/after merging from the base network.

          3. Multi Task Learning: This is a technique in which we learn multiple tasks together, now with this kind of regularisation we can now control before the merge of the layers, how much of the information can be merged.


          these are the quick things i could think of. But there are definitely lots of other uses.



          Vote up, if this helps ;)





          share









          $endgroup$













          • $begingroup$
            Are you a neural network? You're not wrong but that totally doesn't answer my question.
            $endgroup$
            – generic_user
            21 secs ago














          0












          0








          0





          $begingroup$

          Regularisation is a technique to solve overfitting.



          This feature from Keras is going to help a lot in many scenarios. Few times we don't want simpler but a granulr tuning.




          1. CNN: we all know that each convolution layer can contribute to certain set of features from the dataset, and we now a days know what it is trying to do, by defining regularisation to each layer differently, we can better understand how each layer is effecting the final output

          2. Transfer Learning: Where we want learn from the already trained network, and use that domain knowledge. now during this, we can now control, how much we want to regularise before/after merging from the base network.

          3. Multi Task Learning: This is a technique in which we learn multiple tasks together, now with this kind of regularisation we can now control before the merge of the layers, how much of the information can be merged.


          these are the quick things i could think of. But there are definitely lots of other uses.



          Vote up, if this helps ;)





          share









          $endgroup$



          Regularisation is a technique to solve overfitting.



          This feature from Keras is going to help a lot in many scenarios. Few times we don't want simpler but a granulr tuning.




          1. CNN: we all know that each convolution layer can contribute to certain set of features from the dataset, and we now a days know what it is trying to do, by defining regularisation to each layer differently, we can better understand how each layer is effecting the final output

          2. Transfer Learning: Where we want learn from the already trained network, and use that domain knowledge. now during this, we can now control, how much we want to regularise before/after merging from the base network.

          3. Multi Task Learning: This is a technique in which we learn multiple tasks together, now with this kind of regularisation we can now control before the merge of the layers, how much of the information can be merged.


          these are the quick things i could think of. But there are definitely lots of other uses.



          Vote up, if this helps ;)






          share











          share


          share










          answered 8 mins ago









          William ScottWilliam Scott

          1063




          1063












          • $begingroup$
            Are you a neural network? You're not wrong but that totally doesn't answer my question.
            $endgroup$
            – generic_user
            21 secs ago


















          • $begingroup$
            Are you a neural network? You're not wrong but that totally doesn't answer my question.
            $endgroup$
            – generic_user
            21 secs ago
















          $begingroup$
          Are you a neural network? You're not wrong but that totally doesn't answer my question.
          $endgroup$
          – generic_user
          21 secs ago




          $begingroup$
          Are you a neural network? You're not wrong but that totally doesn't answer my question.
          $endgroup$
          – generic_user
          21 secs ago


















          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%2f48384%2fregularization-global-or-layerwise%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

          Callistus I

          Image
          Callistus I Res apud Vicidata repertae: Nativitas : unknown value ; Roma Obitus : 223 ; Roma Pontificatus 217–222 Praecessor : Zephyrinus Successor : Urbanus I Sanctus Callistus qui ieiunium instituit; e libro manu scripto Francogallico saeculo XIV Callistus (natus die ignoto; obiit anno 222), fuit episcopus Romae et Papa Ecclesiae Catholicae Romanae ab anno 217. Vita | Secundum adversarium suum, presbyterem, fuit Hippolytus Callistus, servus argentarii Christiani. Papae Zephyrino, Callistus Romae arcessivit. Callistus fuit primus diaconus ac dux catacumbae apud Viam Appiam, quae hodie Sancti Callisti appellatur. Pontificatus | Nexus externi | Vicimedia Communia plura habent quae ad Callistus I spectant. Fontes Latinae de papis usque ad annum 530 (Papa Felix IV) Liber pontificalis Opera Omnia .mw-parser-output .stipula{padding:3px;background:#F7F8FF;border:1px solid grey;margin:auto}.mw-parser-output .stipula td.cell1{bac...
          Read more

          Tabula Rosettana

          Image
          Tabula multilinguis Rosettana in Museo Britannico ostenditur. Tabula Rosettana, [1] etiam titulo OGIS 90 agnita, est stela decreto de rebus sacris in Aegypto anno 196 a.C.n. lato inscripta. Tabula iuxta Rosettam Aegypti, urbem in delta Nili et ad oram maris Mediterranei iacentem, anno 1799 a milite Francico reperta est. Inventio stelae, linguis duabus scripturisque tribus inscriptae, eruditis Instituti Aegypti statim nuntiata est; ibi enim iussu imperatoris Napoleonis eruditi omnium scientiarum (sub aegide Commissionis Scientiarum et Artium) properaverant cum expeditione Francica. Qua a Britannis mox debellata, tabula Rosettana Londinium missa hodie apud Museum Britannicum iacet. Textus Graecus cito lectus interpretationi textuum Aegyptiorum (in formis hieroglyphica et demotica expressorum) gradatim adiuvit. Denique textum plene interpretatus est Ioannes Franciscus Champollion. Ab opere eruditorum cumulativo coepit hodiernus scripturae hieroglyphicae linguaeque Aegyptiae a...
          Read more

          How to label and detect the document text images

          Image
          1 $begingroup$ This is what I mean as document text image: I want to label the texts in image as separate blocks and my model should detect these labels as classes. NOTE: This is how the end result should be like: The labels like Block 1, Block 2, Block 3,.. should be Logo, Title, Date,.. Others, etc. Work done: First approach : I tried to implement this method via Object Detection, it didn't work. It didn't even detect any text. Second approach : Then I tried it using PixelLink. As this model is build for scene text detection, it detected each and every text in the image. But this method can detect multiple lines of text if the threshold values are increased. But I have no idea how do I add labels to the text blocks. PIXEL_CLS_WEIGHT_all_ones = 'PIXEL_CLS_WEIGHT_all_ones' PIXEL_C...
          Read more