normalization of probabilities in predicting a poly-neuron output in neural nets












1












$begingroup$


When predicting a poly-neuron output in neural nets, say, predicting multiple handwritten digits and giving an output neuron vector (0.1,...,0.9,0.1,...), many use sth like softmax (or sth like the energy dependent probability exponential formula in statistical mechanics) to normalize the output vector such that all the components of the output vector sum up to 1, and that the normalized output vector becomes a probability vector. I doubt the necessity of this normalization, for without which I can equally well predict as per the biggest vector component. Is there anything I overlooked?










share|improve this question









$endgroup$

















    1












    $begingroup$


    When predicting a poly-neuron output in neural nets, say, predicting multiple handwritten digits and giving an output neuron vector (0.1,...,0.9,0.1,...), many use sth like softmax (or sth like the energy dependent probability exponential formula in statistical mechanics) to normalize the output vector such that all the components of the output vector sum up to 1, and that the normalized output vector becomes a probability vector. I doubt the necessity of this normalization, for without which I can equally well predict as per the biggest vector component. Is there anything I overlooked?










    share|improve this question









    $endgroup$















      1












      1








      1


      1



      $begingroup$


      When predicting a poly-neuron output in neural nets, say, predicting multiple handwritten digits and giving an output neuron vector (0.1,...,0.9,0.1,...), many use sth like softmax (or sth like the energy dependent probability exponential formula in statistical mechanics) to normalize the output vector such that all the components of the output vector sum up to 1, and that the normalized output vector becomes a probability vector. I doubt the necessity of this normalization, for without which I can equally well predict as per the biggest vector component. Is there anything I overlooked?










      share|improve this question









      $endgroup$




      When predicting a poly-neuron output in neural nets, say, predicting multiple handwritten digits and giving an output neuron vector (0.1,...,0.9,0.1,...), many use sth like softmax (or sth like the energy dependent probability exponential formula in statistical mechanics) to normalize the output vector such that all the components of the output vector sum up to 1, and that the normalized output vector becomes a probability vector. I doubt the necessity of this normalization, for without which I can equally well predict as per the biggest vector component. Is there anything I overlooked?







      neural-network normalization






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Nov 9 '18 at 10:21









      feynmanfeynman

      1578




      1578






















          2 Answers
          2






          active

          oldest

          votes


















          1












          $begingroup$

          You are correct, but this is not called normalization. You can simply use the highest probability output for category. This is what softmax does for you. For example 2 output neurons can have 0.1 for dog and 0.9 for cat as the loss. Softmax will it just convert it to [0,1] meaning no dog but a cat is on the image.






          share|improve this answer









          $endgroup$













          • $begingroup$
            What I mean by normalization is that softmax makes the components of the probability vector sum up to 1, which I don't deem a must. That's clear, I won't use softmax for this sheer aesthetic piece of pleasure.
            $endgroup$
            – feynman
            Nov 11 '18 at 9:23










          • $begingroup$
            You can do that as well. But if your loss is for example categorical_crossentropy then a softmax is needed because crossentropy requires a one-hot output.
            $endgroup$
            – Manngo
            Nov 11 '18 at 19:59










          • $begingroup$
            @ Manngo Sorry I don't get what you mean by categorical. If I have several digits to recognize, is that what you mean?
            $endgroup$
            – feynman
            Nov 12 '18 at 11:11










          • $begingroup$
            categorical_crossentropy loss requites data encoded as on-hot method as categories like [0,0,0,0,1,0,0,0]. This is what softmax does.
            $endgroup$
            – Manngo
            Nov 13 '18 at 10:23



















          0












          $begingroup$

          Yes, you have overlooked something. Let me explain this with an example:



          When training a neural network, you use the loss function as a signal to backpropagation. Now let us say that you have a network which outputs three categories: Cat, Dog, and Toad. Let's say the prediction of the network in an iteration is [0.7, 0.6, 0.3], although the data is, in fact, an image of a dog, meaning the truth is: [0 1 0].



          Without a softmax layer, you cannot really tell much the network got the prediction wrong. In this example you might think the difference is 0.7 - 0.6 = 0.1, however after running a softmax, you realize that it is in fact 0.03, since the network was very strong in differentiating between the Toad category vs. Dog and Cat, so the loss is not as big as it seems.



          Now as an experiment, run a neural network without the softmax layer and see for yourself, how severe it can affect the training. Not only that, but normalization of the input batches also makes a huge difference in training a network.






          share|improve this answer








          New contributor




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






          $endgroup$













            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%2f40955%2fnormalization-of-probabilities-in-predicting-a-poly-neuron-output-in-neural-nets%23new-answer', 'question_page');
            }
            );

            Post as a guest















            Required, but never shown

























            2 Answers
            2






            active

            oldest

            votes








            2 Answers
            2






            active

            oldest

            votes









            active

            oldest

            votes






            active

            oldest

            votes









            1












            $begingroup$

            You are correct, but this is not called normalization. You can simply use the highest probability output for category. This is what softmax does for you. For example 2 output neurons can have 0.1 for dog and 0.9 for cat as the loss. Softmax will it just convert it to [0,1] meaning no dog but a cat is on the image.






            share|improve this answer









            $endgroup$













            • $begingroup$
              What I mean by normalization is that softmax makes the components of the probability vector sum up to 1, which I don't deem a must. That's clear, I won't use softmax for this sheer aesthetic piece of pleasure.
              $endgroup$
              – feynman
              Nov 11 '18 at 9:23










            • $begingroup$
              You can do that as well. But if your loss is for example categorical_crossentropy then a softmax is needed because crossentropy requires a one-hot output.
              $endgroup$
              – Manngo
              Nov 11 '18 at 19:59










            • $begingroup$
              @ Manngo Sorry I don't get what you mean by categorical. If I have several digits to recognize, is that what you mean?
              $endgroup$
              – feynman
              Nov 12 '18 at 11:11










            • $begingroup$
              categorical_crossentropy loss requites data encoded as on-hot method as categories like [0,0,0,0,1,0,0,0]. This is what softmax does.
              $endgroup$
              – Manngo
              Nov 13 '18 at 10:23
















            1












            $begingroup$

            You are correct, but this is not called normalization. You can simply use the highest probability output for category. This is what softmax does for you. For example 2 output neurons can have 0.1 for dog and 0.9 for cat as the loss. Softmax will it just convert it to [0,1] meaning no dog but a cat is on the image.






            share|improve this answer









            $endgroup$













            • $begingroup$
              What I mean by normalization is that softmax makes the components of the probability vector sum up to 1, which I don't deem a must. That's clear, I won't use softmax for this sheer aesthetic piece of pleasure.
              $endgroup$
              – feynman
              Nov 11 '18 at 9:23










            • $begingroup$
              You can do that as well. But if your loss is for example categorical_crossentropy then a softmax is needed because crossentropy requires a one-hot output.
              $endgroup$
              – Manngo
              Nov 11 '18 at 19:59










            • $begingroup$
              @ Manngo Sorry I don't get what you mean by categorical. If I have several digits to recognize, is that what you mean?
              $endgroup$
              – feynman
              Nov 12 '18 at 11:11










            • $begingroup$
              categorical_crossentropy loss requites data encoded as on-hot method as categories like [0,0,0,0,1,0,0,0]. This is what softmax does.
              $endgroup$
              – Manngo
              Nov 13 '18 at 10:23














            1












            1








            1





            $begingroup$

            You are correct, but this is not called normalization. You can simply use the highest probability output for category. This is what softmax does for you. For example 2 output neurons can have 0.1 for dog and 0.9 for cat as the loss. Softmax will it just convert it to [0,1] meaning no dog but a cat is on the image.






            share|improve this answer









            $endgroup$



            You are correct, but this is not called normalization. You can simply use the highest probability output for category. This is what softmax does for you. For example 2 output neurons can have 0.1 for dog and 0.9 for cat as the loss. Softmax will it just convert it to [0,1] meaning no dog but a cat is on the image.







            share|improve this answer












            share|improve this answer



            share|improve this answer










            answered Nov 10 '18 at 22:02









            ManngoManngo

            1734




            1734












            • $begingroup$
              What I mean by normalization is that softmax makes the components of the probability vector sum up to 1, which I don't deem a must. That's clear, I won't use softmax for this sheer aesthetic piece of pleasure.
              $endgroup$
              – feynman
              Nov 11 '18 at 9:23










            • $begingroup$
              You can do that as well. But if your loss is for example categorical_crossentropy then a softmax is needed because crossentropy requires a one-hot output.
              $endgroup$
              – Manngo
              Nov 11 '18 at 19:59










            • $begingroup$
              @ Manngo Sorry I don't get what you mean by categorical. If I have several digits to recognize, is that what you mean?
              $endgroup$
              – feynman
              Nov 12 '18 at 11:11










            • $begingroup$
              categorical_crossentropy loss requites data encoded as on-hot method as categories like [0,0,0,0,1,0,0,0]. This is what softmax does.
              $endgroup$
              – Manngo
              Nov 13 '18 at 10:23


















            • $begingroup$
              What I mean by normalization is that softmax makes the components of the probability vector sum up to 1, which I don't deem a must. That's clear, I won't use softmax for this sheer aesthetic piece of pleasure.
              $endgroup$
              – feynman
              Nov 11 '18 at 9:23










            • $begingroup$
              You can do that as well. But if your loss is for example categorical_crossentropy then a softmax is needed because crossentropy requires a one-hot output.
              $endgroup$
              – Manngo
              Nov 11 '18 at 19:59










            • $begingroup$
              @ Manngo Sorry I don't get what you mean by categorical. If I have several digits to recognize, is that what you mean?
              $endgroup$
              – feynman
              Nov 12 '18 at 11:11










            • $begingroup$
              categorical_crossentropy loss requites data encoded as on-hot method as categories like [0,0,0,0,1,0,0,0]. This is what softmax does.
              $endgroup$
              – Manngo
              Nov 13 '18 at 10:23
















            $begingroup$
            What I mean by normalization is that softmax makes the components of the probability vector sum up to 1, which I don't deem a must. That's clear, I won't use softmax for this sheer aesthetic piece of pleasure.
            $endgroup$
            – feynman
            Nov 11 '18 at 9:23




            $begingroup$
            What I mean by normalization is that softmax makes the components of the probability vector sum up to 1, which I don't deem a must. That's clear, I won't use softmax for this sheer aesthetic piece of pleasure.
            $endgroup$
            – feynman
            Nov 11 '18 at 9:23












            $begingroup$
            You can do that as well. But if your loss is for example categorical_crossentropy then a softmax is needed because crossentropy requires a one-hot output.
            $endgroup$
            – Manngo
            Nov 11 '18 at 19:59




            $begingroup$
            You can do that as well. But if your loss is for example categorical_crossentropy then a softmax is needed because crossentropy requires a one-hot output.
            $endgroup$
            – Manngo
            Nov 11 '18 at 19:59












            $begingroup$
            @ Manngo Sorry I don't get what you mean by categorical. If I have several digits to recognize, is that what you mean?
            $endgroup$
            – feynman
            Nov 12 '18 at 11:11




            $begingroup$
            @ Manngo Sorry I don't get what you mean by categorical. If I have several digits to recognize, is that what you mean?
            $endgroup$
            – feynman
            Nov 12 '18 at 11:11












            $begingroup$
            categorical_crossentropy loss requites data encoded as on-hot method as categories like [0,0,0,0,1,0,0,0]. This is what softmax does.
            $endgroup$
            – Manngo
            Nov 13 '18 at 10:23




            $begingroup$
            categorical_crossentropy loss requites data encoded as on-hot method as categories like [0,0,0,0,1,0,0,0]. This is what softmax does.
            $endgroup$
            – Manngo
            Nov 13 '18 at 10:23











            0












            $begingroup$

            Yes, you have overlooked something. Let me explain this with an example:



            When training a neural network, you use the loss function as a signal to backpropagation. Now let us say that you have a network which outputs three categories: Cat, Dog, and Toad. Let's say the prediction of the network in an iteration is [0.7, 0.6, 0.3], although the data is, in fact, an image of a dog, meaning the truth is: [0 1 0].



            Without a softmax layer, you cannot really tell much the network got the prediction wrong. In this example you might think the difference is 0.7 - 0.6 = 0.1, however after running a softmax, you realize that it is in fact 0.03, since the network was very strong in differentiating between the Toad category vs. Dog and Cat, so the loss is not as big as it seems.



            Now as an experiment, run a neural network without the softmax layer and see for yourself, how severe it can affect the training. Not only that, but normalization of the input batches also makes a huge difference in training a network.






            share|improve this answer








            New contributor




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






            $endgroup$


















              0












              $begingroup$

              Yes, you have overlooked something. Let me explain this with an example:



              When training a neural network, you use the loss function as a signal to backpropagation. Now let us say that you have a network which outputs three categories: Cat, Dog, and Toad. Let's say the prediction of the network in an iteration is [0.7, 0.6, 0.3], although the data is, in fact, an image of a dog, meaning the truth is: [0 1 0].



              Without a softmax layer, you cannot really tell much the network got the prediction wrong. In this example you might think the difference is 0.7 - 0.6 = 0.1, however after running a softmax, you realize that it is in fact 0.03, since the network was very strong in differentiating between the Toad category vs. Dog and Cat, so the loss is not as big as it seems.



              Now as an experiment, run a neural network without the softmax layer and see for yourself, how severe it can affect the training. Not only that, but normalization of the input batches also makes a huge difference in training a network.






              share|improve this answer








              New contributor




              ambodi 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





                $begingroup$

                Yes, you have overlooked something. Let me explain this with an example:



                When training a neural network, you use the loss function as a signal to backpropagation. Now let us say that you have a network which outputs three categories: Cat, Dog, and Toad. Let's say the prediction of the network in an iteration is [0.7, 0.6, 0.3], although the data is, in fact, an image of a dog, meaning the truth is: [0 1 0].



                Without a softmax layer, you cannot really tell much the network got the prediction wrong. In this example you might think the difference is 0.7 - 0.6 = 0.1, however after running a softmax, you realize that it is in fact 0.03, since the network was very strong in differentiating between the Toad category vs. Dog and Cat, so the loss is not as big as it seems.



                Now as an experiment, run a neural network without the softmax layer and see for yourself, how severe it can affect the training. Not only that, but normalization of the input batches also makes a huge difference in training a network.






                share|improve this answer








                New contributor




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






                $endgroup$



                Yes, you have overlooked something. Let me explain this with an example:



                When training a neural network, you use the loss function as a signal to backpropagation. Now let us say that you have a network which outputs three categories: Cat, Dog, and Toad. Let's say the prediction of the network in an iteration is [0.7, 0.6, 0.3], although the data is, in fact, an image of a dog, meaning the truth is: [0 1 0].



                Without a softmax layer, you cannot really tell much the network got the prediction wrong. In this example you might think the difference is 0.7 - 0.6 = 0.1, however after running a softmax, you realize that it is in fact 0.03, since the network was very strong in differentiating between the Toad category vs. Dog and Cat, so the loss is not as big as it seems.



                Now as an experiment, run a neural network without the softmax layer and see for yourself, how severe it can affect the training. Not only that, but normalization of the input batches also makes a huge difference in training a network.







                share|improve this answer








                New contributor




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









                share|improve this answer



                share|improve this answer






                New contributor




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









                answered 17 hours ago









                ambodiambodi

                1011




                1011




                New contributor




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





                New contributor





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






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






























                    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%2f40955%2fnormalization-of-probabilities-in-predicting-a-poly-neuron-output-in-neural-nets%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