Learning curve of CNN model Announcing the arrival of Valued Associate #679: Cesar Manara Planned maintenance scheduled April 23, 2019 at 23:30 UTC (7:30pm US/Eastern) 2019 Moderator Election Q&A - Questionnaire 2019 Community Moderator Election ResultsNeural net learning only one class?Convolution Neural Network Loss and performanceVery low accuracy of new data compared to validation dataDifficulty in choosing Hyperparameters for my CNNMatlab: setting static iterations per epoch in a CNNKeras: Prediction performance does not match accuracyLoss is bad, but accuracy increases?Validation loss increases and validation accuracy decreasesWhy does my minimal CNN example show strongly fluctuating validation loss?Kappa Goes up as Accuracy Goes Down
How much damage would a cupful of neutron star matter do to the Earth?
What is a more techy Technical Writer job title that isn't cutesy or confusing?
Is there public access to the Meteor Crater in Arizona?
How to change the tick of the color bar legend to black
What adaptations would allow standard fantasy dwarves to survive in the desert?
Nose gear failure in single prop aircraft: belly landing or nose-gear up landing?
What is the difference between a "ranged attack" and a "ranged weapon attack"?
How to ternary Plot3D a function
What initially awakened the Balrog?
My mentor says to set image to Fine instead of RAW — how is this different from JPG?
Does silver oxide react with hydrogen sulfide?
In musical terms, what properties are varied by the human voice to produce different words / syllables?
Why not send Voyager 3 and 4 following up the paths taken by Voyager 1 and 2 to re-transmit signals of later as they fly away from Earth?
Is it dangerous to install hacking tools on my private linux machine?
Asymptotics question
What does it mean that physics no longer uses mechanical models to describe phenomena?
Does the Mueller report show a conspiracy between Russia and the Trump Campaign?
Why weren't discrete x86 CPUs ever used in game hardware?
Positioning dot before text in math mode
Random body shuffle every night—can we still function?
Why complex landing gears are used instead of simple,reliability and light weight muscle wire or shape memory alloys?
Did any compiler fully use 80-bit floating point?
Would color changing eyes affect vision?
As a dual citizen, my US passport will expire one day after traveling to the US. Will this work?
Learning curve of CNN model
Announcing the arrival of Valued Associate #679: Cesar Manara
Planned maintenance scheduled April 23, 2019 at 23:30 UTC (7:30pm US/Eastern)
2019 Moderator Election Q&A - Questionnaire
2019 Community Moderator Election ResultsNeural net learning only one class?Convolution Neural Network Loss and performanceVery low accuracy of new data compared to validation dataDifficulty in choosing Hyperparameters for my CNNMatlab: setting static iterations per epoch in a CNNKeras: Prediction performance does not match accuracyLoss is bad, but accuracy increases?Validation loss increases and validation accuracy decreasesWhy does my minimal CNN example show strongly fluctuating validation loss?Kappa Goes up as Accuracy Goes Down
$begingroup$
I have a graph for a model on train accuracy and validation accuracy:
But I'm having trouble interpreting it. By the way i interpreted, I would say it is of poor performance. But I would like to know how this graph is interpreted in a more broad manner.
As in if we were to look at the point where the validation acc begins to bisect the train acc line, and went all the way down, what does this indicate? Would appreciate some help on this as I'm horrible at interpreting graphs.
machine-learning neural-network deep-learning cnn
asked Apr 4 at 4:10
MaxxxMaxxx
1324
$endgroup$
add a comment |
$begingroup$
I have a graph for a model on train accuracy and validation accuracy:
But I'm having trouble interpreting it. By the way i interpreted, I would say it is of poor performance. But I would like to know how this graph is interpreted in a more broad manner.
As in if we were to look at the point where the validation acc begins to bisect the train acc line, and went all the way down, what does this indicate? Would appreciate some help on this as I'm horrible at interpreting graphs.
machine-learning neural-network deep-learning cnn
asked Apr 4 at 4:10
MaxxxMaxxx
1324
$endgroup$
add a comment |
$begingroup$
I have a graph for a model on train accuracy and validation accuracy:
But I'm having trouble interpreting it. By the way i interpreted, I would say it is of poor performance. But I would like to know how this graph is interpreted in a more broad manner.
As in if we were to look at the point where the validation acc begins to bisect the train acc line, and went all the way down, what does this indicate? Would appreciate some help on this as I'm horrible at interpreting graphs.
machine-learning neural-network deep-learning cnn
asked Apr 4 at 4:10
MaxxxMaxxx
1324
$endgroup$
I have a graph for a model on train accuracy and validation accuracy:
But I'm having trouble interpreting it. By the way i interpreted, I would say it is of poor performance. But I would like to know how this graph is interpreted in a more broad manner.
As in if we were to look at the point where the validation acc begins to bisect the train acc line, and went all the way down, what does this indicate? Would appreciate some help on this as I'm horrible at interpreting graphs.
machine-learning neural-network deep-learning cnn
machine-learning neural-network deep-learning cnn
asked Apr 4 at 4:10
MaxxxMaxxx
1324
asked Apr 4 at 4:10
MaxxxMaxxx
1324
asked Apr 4 at 4:10
MaxxxMaxxx
1324
asked Apr 4 at 4:10
MaxxxMaxxx
1324
asked Apr 4 at 4:10
MaxxxMaxxx
1324
1324
add a comment |
add a comment |
2 Answers
2
active
oldest
votes
$begingroup$
https://en.wikipedia.org/wiki/Overfitting
This model is over-fitting. Better train accuracy (and validation accuracy that gets worse with successive iterations) indicates over-fit.
For CNN Next steps should be to reduce complexity of the model and adding droputs / batch normalization.
Few articles on this :
https://towardsdatascience.com/handling-overfitting-in-deep-learning-models-c760ee047c6e
https://machinelearningmastery.com/how-to-reduce-overfitting-with-dropout-regularization-in-keras/
answered Apr 4 at 8:30
Shamit VermaShamit Verma
1,6391414
$endgroup$
add a comment |
$begingroup$
I think there is a bug. Or too little data. The training accuracy is - in the best case - close to the validation accuracy. That the validation accuracy gets lower than the training accuracy is a strong indicator for a bug. Or too little data, which means the difference of 2% might not be relevant.
answered Apr 4 at 5:03
Martin ThomaMartin Thoma
6,7781657135
$endgroup$
add a comment |
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
);
);
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48566%2flearning-curve-of-cnn-model%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
$begingroup$
https://en.wikipedia.org/wiki/Overfitting
This model is over-fitting. Better train accuracy (and validation accuracy that gets worse with successive iterations) indicates over-fit.
For CNN Next steps should be to reduce complexity of the model and adding droputs / batch normalization.
Few articles on this :
https://towardsdatascience.com/handling-overfitting-in-deep-learning-models-c760ee047c6e
https://machinelearningmastery.com/how-to-reduce-overfitting-with-dropout-regularization-in-keras/
answered Apr 4 at 8:30
Shamit VermaShamit Verma
1,6391414
$endgroup$
add a comment |
$begingroup$
https://en.wikipedia.org/wiki/Overfitting
This model is over-fitting. Better train accuracy (and validation accuracy that gets worse with successive iterations) indicates over-fit.
For CNN Next steps should be to reduce complexity of the model and adding droputs / batch normalization.
Few articles on this :
https://towardsdatascience.com/handling-overfitting-in-deep-learning-models-c760ee047c6e
https://machinelearningmastery.com/how-to-reduce-overfitting-with-dropout-regularization-in-keras/
answered Apr 4 at 8:30
Shamit VermaShamit Verma
1,6391414
$endgroup$
add a comment |
$begingroup$
https://en.wikipedia.org/wiki/Overfitting
This model is over-fitting. Better train accuracy (and validation accuracy that gets worse with successive iterations) indicates over-fit.
For CNN Next steps should be to reduce complexity of the model and adding droputs / batch normalization.
Few articles on this :
https://towardsdatascience.com/handling-overfitting-in-deep-learning-models-c760ee047c6e
https://machinelearningmastery.com/how-to-reduce-overfitting-with-dropout-regularization-in-keras/
answered Apr 4 at 8:30
Shamit VermaShamit Verma
1,6391414
$endgroup$
https://en.wikipedia.org/wiki/Overfitting
This model is over-fitting. Better train accuracy (and validation accuracy that gets worse with successive iterations) indicates over-fit.
For CNN Next steps should be to reduce complexity of the model and adding droputs / batch normalization.
Few articles on this :
https://towardsdatascience.com/handling-overfitting-in-deep-learning-models-c760ee047c6e
https://machinelearningmastery.com/how-to-reduce-overfitting-with-dropout-regularization-in-keras/
answered Apr 4 at 8:30
Shamit VermaShamit Verma
1,6391414
answered Apr 4 at 8:30
Shamit VermaShamit Verma
1,6391414
answered Apr 4 at 8:30
Shamit VermaShamit Verma
1,6391414
answered Apr 4 at 8:30
Shamit VermaShamit Verma
1,6391414
1,6391414
add a comment |
add a comment |
$begingroup$
I think there is a bug. Or too little data. The training accuracy is - in the best case - close to the validation accuracy. That the validation accuracy gets lower than the training accuracy is a strong indicator for a bug. Or too little data, which means the difference of 2% might not be relevant.
answered Apr 4 at 5:03
Martin ThomaMartin Thoma
6,7781657135
$endgroup$
add a comment |
$begingroup$
I think there is a bug. Or too little data. The training accuracy is - in the best case - close to the validation accuracy. That the validation accuracy gets lower than the training accuracy is a strong indicator for a bug. Or too little data, which means the difference of 2% might not be relevant.
answered Apr 4 at 5:03
Martin ThomaMartin Thoma
6,7781657135
$endgroup$
add a comment |
$begingroup$
I think there is a bug. Or too little data. The training accuracy is - in the best case - close to the validation accuracy. That the validation accuracy gets lower than the training accuracy is a strong indicator for a bug. Or too little data, which means the difference of 2% might not be relevant.
answered Apr 4 at 5:03
Martin ThomaMartin Thoma
6,7781657135
$endgroup$
I think there is a bug. Or too little data. The training accuracy is - in the best case - close to the validation accuracy. That the validation accuracy gets lower than the training accuracy is a strong indicator for a bug. Or too little data, which means the difference of 2% might not be relevant.
answered Apr 4 at 5:03
Martin ThomaMartin Thoma
6,7781657135
answered Apr 4 at 5:03
Martin ThomaMartin Thoma
6,7781657135
answered Apr 4 at 5:03
Martin ThomaMartin Thoma
6,7781657135
answered Apr 4 at 5:03
Martin ThomaMartin Thoma
6,7781657135
6,7781657135
add a comment |
add a comment |
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.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48566%2flearning-curve-of-cnn-model%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
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
