Which learning paradigm (e.g. supervised, self-supervised, unsupervised, reinforcement learning) do brains use to acquire visual skills?2019 Community Moderator ElectionCan I use unsupervised learning followed by supervised learning?Which type of machine learning to useWhich supervised learning algorithms are available for matching?Is what I did supervised or unsupervised Machine learning?How to use deep learning to add local (e.g. repairing) transformations to images?Training an AI to play Starcraft 2 with superhuman level of performance?Supervised Learning could be biased if we use obsolete dataWhat machine learning algorithms to use for unsupervised POS tagging?Reinforcement learning - How to deal with varying number of actions which do number approximationWhich reinforcement learning methods can be trained off-policy?

Facing a paradox: Earnshaw's theorem in one dimension

Blender 2.8 I can't see vertices, edges or faces in edit mode

How can I fix/modify my tub/shower combo so the water comes out of the showerhead?

SSH "lag" in LAN on some machines, mixed distros

How to say in German "enjoying home comforts"

What is the word for reserving something for yourself before others do?

What about the virus in 12 Monkeys?

Can one be a co-translator of a book, if he does not know the language that the book is translated into?

What to put in ESTA if staying in US for a few days before going on to Canada

How to prevent "they're falling in love" trope

What is the most common color to indicate the input-field is disabled?

Took a trip to a parallel universe, need help deciphering

A reference to a well-known characterization of scattered compact spaces

Can a rocket refuel on Mars from water?

What killed these X2 caps?

Stopping power of mountain vs road bike

I Accidentally Deleted a Stock Terminal Theme

What's the point of deactivating Num Lock on login screens?

I'm flying to France today and my passport expires in less than 2 months

Why does Kotter return in Welcome Back Kotter

How can I make my BBEG immortal short of making them a Lich or Vampire?

Why is it a bad idea to hire a hitman to eliminate most corrupt politicians?

Could gravitational lensing be used to protect a spaceship from a laser?

Assassin's bullet with mercury



Which learning paradigm (e.g. supervised, self-supervised, unsupervised, reinforcement learning) do brains use to acquire visual skills?



2019 Community Moderator ElectionCan I use unsupervised learning followed by supervised learning?Which type of machine learning to useWhich supervised learning algorithms are available for matching?Is what I did supervised or unsupervised Machine learning?How to use deep learning to add local (e.g. repairing) transformations to images?Training an AI to play Starcraft 2 with superhuman level of performance?Supervised Learning could be biased if we use obsolete dataWhat machine learning algorithms to use for unsupervised POS tagging?Reinforcement learning - How to deal with varying number of actions which do number approximationWhich reinforcement learning methods can be trained off-policy?










0












$begingroup$


In computer vision is very common to use supervised tasks, where datasets have to be manually annotated by humans. Some examples are object classification (class labels), detection (bounding boxes) and segmentation (pixel-level masks). But animals don't need anybody to show them bounding boxes or masks on top of things in order for them to develop the visual skills to detect objects and make sense of the visual world around them. My educated guess is that brains must be performing some kind of self-supervision to train their visual neural networks. Does anybody know which learning paradigm are brains using to achieve such an outstanding level of visual competence? Are there any works on replicating this paradigm in computer vision?










share|improve this question











$endgroup$
















    0












    $begingroup$


    In computer vision is very common to use supervised tasks, where datasets have to be manually annotated by humans. Some examples are object classification (class labels), detection (bounding boxes) and segmentation (pixel-level masks). But animals don't need anybody to show them bounding boxes or masks on top of things in order for them to develop the visual skills to detect objects and make sense of the visual world around them. My educated guess is that brains must be performing some kind of self-supervision to train their visual neural networks. Does anybody know which learning paradigm are brains using to achieve such an outstanding level of visual competence? Are there any works on replicating this paradigm in computer vision?










    share|improve this question











    $endgroup$














      0












      0








      0





      $begingroup$


      In computer vision is very common to use supervised tasks, where datasets have to be manually annotated by humans. Some examples are object classification (class labels), detection (bounding boxes) and segmentation (pixel-level masks). But animals don't need anybody to show them bounding boxes or masks on top of things in order for them to develop the visual skills to detect objects and make sense of the visual world around them. My educated guess is that brains must be performing some kind of self-supervision to train their visual neural networks. Does anybody know which learning paradigm are brains using to achieve such an outstanding level of visual competence? Are there any works on replicating this paradigm in computer vision?










      share|improve this question











      $endgroup$




      In computer vision is very common to use supervised tasks, where datasets have to be manually annotated by humans. Some examples are object classification (class labels), detection (bounding boxes) and segmentation (pixel-level masks). But animals don't need anybody to show them bounding boxes or masks on top of things in order for them to develop the visual skills to detect objects and make sense of the visual world around them. My educated guess is that brains must be performing some kind of self-supervision to train their visual neural networks. Does anybody know which learning paradigm are brains using to achieve such an outstanding level of visual competence? Are there any works on replicating this paradigm in computer vision?







      machine-learning neural-network computer-vision






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited 11 mins ago







      Pablo Messina

















      asked 18 mins ago









      Pablo MessinaPablo Messina

      435




      435




















          0






          active

          oldest

          votes












          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%2f48645%2fwhich-learning-paradigm-e-g-supervised-self-supervised-unsupervised-reinfor%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















          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%2f48645%2fwhich-learning-paradigm-e-g-supervised-self-supervised-unsupervised-reinfor%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

          ValueError: Error when checking input: expected conv2d_13_input to have shape (3, 150, 150) but got array with shape (150, 150, 3)2019 Community Moderator ElectionError when checking : expected dense_1_input to have shape (None, 5) but got array with shape (200, 1)Error 'Expected 2D array, got 1D array instead:'ValueError: Error when checking input: expected lstm_41_input to have 3 dimensions, but got array with shape (40000,100)ValueError: Error when checking target: expected dense_1 to have shape (7,) but got array with shape (1,)ValueError: Error when checking target: expected dense_2 to have shape (1,) but got array with shape (0,)Keras exception: ValueError: Error when checking input: expected conv2d_1_input to have shape (150, 150, 3) but got array with shape (256, 256, 3)Steps taking too long to completewhen checking input: expected dense_1_input to have shape (13328,) but got array with shape (317,)ValueError: Error when checking target: expected dense_3 to have shape (None, 1) but got array with shape (7715, 40000)Keras exception: Error when checking input: expected dense_input to have shape (2,) but got array with shape (1,)

          Ружовы пелікан Змест Знешні выгляд | Пашырэнне | Асаблівасці біялогіі | Літаратура | НавігацыяДагледжаная версіяправерана1 зменаДагледжаная версіяправерана1 змена/ 22697590 Сістэматыкана ВіківідахВыявына Вікісховішчы174693363011049382

          Illegal assignment from SObject to ContactFetching String, Id from Map - Illegal Assignment Id to Field / ObjectError: Compile Error: Illegal assignment from String to BooleanError: List has no rows for assignment to SObjectError on Test Class - System.QueryException: List has no rows for assignment to SObjectRemote action problemDML requires SObject or SObject list type error“Illegal assignment from List to List”Test Class Fail: Batch Class: System.QueryException: List has no rows for assignment to SObjectMapping to a user'List has no rows for assignment to SObject' Mystery