Deep learning not classify some classes 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 ResultsConvolutional Neural Network not learning EEG dataHow do I provide input and output for such a network structure in kerasWhat is the best way to classify data not belonging to set of classes?Classification of a time series dataHow to Classify an Image in a Class and a Subclass?Number of classes in SOMHow do we predict what is in an image using unsupervised deep neural networks?Training Accuracy stuck in KerasAre there cases where tree based algorithms can do better than neural networks?Should estimated probabilities from multi class classification sum to 1
Writing a T-SQL stored procedure to receive 4 numbers and insert them into a table
What helicopter has the most rotor blades?
Is there a verb for listening stealthily?
What does the black goddess statue do and what is it?
Not within Jobscope - Aggravated injury
Will I be more secure with my own router behind my ISP's router?
Married in secret, can marital status in passport be changed at a later date?
Can't solve system of linear equations (that need simplification first)
How to begin with a paragraph in latex
Preserving file and folder permissions with rsync
What is a 'Key' in computer science?
Can gravitational waves pass through a black hole?
Is there a way to fake a method response using Mock or Stubs?
What is ls Largest Number Formed by only moving two sticks in 508?
Has a Nobel Peace laureate ever been accused of war crimes?
How was Lagrange appointed professor of mathematics so early?
What's called a person who work as someone who puts products on shelves in stores?
Is there a possibility to generate a list dynamically in Latex?
What happened to Viserion in Season 7?
Israeli soda type drink
VBA: Single line if statement with multiple actions
How can I wire a 9-position switch so that each position turns on one more LED than the one before?
Why does Java have support for time zone offsets with seconds precision?
Does Prince Arnaud cause someone holding the Princess to lose?
Deep learning not classify some classes
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 ResultsConvolutional Neural Network not learning EEG dataHow do I provide input and output for such a network structure in kerasWhat is the best way to classify data not belonging to set of classes?Classification of a time series dataHow to Classify an Image in a Class and a Subclass?Number of classes in SOMHow do we predict what is in an image using unsupervised deep neural networks?Training Accuracy stuck in KerasAre there cases where tree based algorithms can do better than neural networks?Should estimated probabilities from multi class classification sum to 1
$begingroup$
I want to classify 13 classes, but 2 classes is not classified.
This is the test result.
As you can see in the image, class 3 and class 11 is not detected.
It's simple vector to class classification.
The dimension of input is 16 and I've added 2 dense layers in the model.
What do I need to add to model?
machine-learning classification data
asked 3 hours ago
Maxim DavidMaxim David
1
New contributor
Maxim David is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
I want to classify 13 classes, but 2 classes is not classified.
This is the test result.
As you can see in the image, class 3 and class 11 is not detected.
It's simple vector to class classification.
The dimension of input is 16 and I've added 2 dense layers in the model.
What do I need to add to model?
machine-learning classification data
asked 3 hours ago
Maxim DavidMaxim David
1
New contributor
Maxim David is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
$begingroup$
Could you provide a bit of context for the problem. Are your classes ordered or are they independent? Are you passing the label as an integer or is it one-hot encoded? I'm asking these questions because from what I can see, for example for class no. 3, your model is predicting the nearest classes (i.e. 2 and 4).
$endgroup$
– Djib2011
36 mins ago
$begingroup$
You can't always assume that your results would lead to 100% accuracy. With no context, I can only suspect that the differentiation between those 2 particular classes, with all other classes, is weak. Also, maybe they are minority classes and your model is ignoring them. You need to provide some more insight into your data.
$endgroup$
– Sterls
21 mins ago
$begingroup$
the classes are ordered, and label is one-hot encoded.
$endgroup$
– Maxim David
10 mins ago
$begingroup$
Here's the link of data dropbox.com/s/a4ea6t7m102b0j8/person1_2_3_EEG_set1.zip?dl=0
$endgroup$
– Maxim David
9 mins ago
$begingroup$
Hmm, I added one more layer and now the accuracy is 100%. I'm not sure the result is correct.
$endgroup$
– Maxim David
7 mins ago
add a comment |
$begingroup$
I want to classify 13 classes, but 2 classes is not classified.
This is the test result.
As you can see in the image, class 3 and class 11 is not detected.
It's simple vector to class classification.
The dimension of input is 16 and I've added 2 dense layers in the model.
What do I need to add to model?
machine-learning classification data
asked 3 hours ago
Maxim DavidMaxim David
1
New contributor
Maxim David is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I want to classify 13 classes, but 2 classes is not classified.
This is the test result.
As you can see in the image, class 3 and class 11 is not detected.
It's simple vector to class classification.
The dimension of input is 16 and I've added 2 dense layers in the model.
What do I need to add to model?
machine-learning classification data
machine-learning classification data
asked 3 hours ago
Maxim DavidMaxim David
1
New contributor
Maxim David is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 3 hours ago
Maxim DavidMaxim David
1
New contributor
Maxim David is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 3 hours ago
Maxim DavidMaxim David
1
New contributor
Maxim David is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 3 hours ago
Maxim DavidMaxim David
1
asked 3 hours ago
Maxim DavidMaxim David
1
1
New contributor
Maxim David is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
Maxim David is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Maxim David is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$begingroup$
Could you provide a bit of context for the problem. Are your classes ordered or are they independent? Are you passing the label as an integer or is it one-hot encoded? I'm asking these questions because from what I can see, for example for class no. 3, your model is predicting the nearest classes (i.e. 2 and 4).
$endgroup$
– Djib2011
36 mins ago
$begingroup$
You can't always assume that your results would lead to 100% accuracy. With no context, I can only suspect that the differentiation between those 2 particular classes, with all other classes, is weak. Also, maybe they are minority classes and your model is ignoring them. You need to provide some more insight into your data.
$endgroup$
– Sterls
21 mins ago
$begingroup$
the classes are ordered, and label is one-hot encoded.
$endgroup$
– Maxim David
10 mins ago
$begingroup$
Here's the link of data dropbox.com/s/a4ea6t7m102b0j8/person1_2_3_EEG_set1.zip?dl=0
$endgroup$
– Maxim David
9 mins ago
$begingroup$
Hmm, I added one more layer and now the accuracy is 100%. I'm not sure the result is correct.
$endgroup$
– Maxim David
7 mins ago
add a comment |
$begingroup$
Could you provide a bit of context for the problem. Are your classes ordered or are they independent? Are you passing the label as an integer or is it one-hot encoded? I'm asking these questions because from what I can see, for example for class no. 3, your model is predicting the nearest classes (i.e. 2 and 4).
$endgroup$
– Djib2011
36 mins ago
$begingroup$
You can't always assume that your results would lead to 100% accuracy. With no context, I can only suspect that the differentiation between those 2 particular classes, with all other classes, is weak. Also, maybe they are minority classes and your model is ignoring them. You need to provide some more insight into your data.
$endgroup$
– Sterls
21 mins ago
$begingroup$
the classes are ordered, and label is one-hot encoded.
$endgroup$
– Maxim David
10 mins ago
$begingroup$
Here's the link of data dropbox.com/s/a4ea6t7m102b0j8/person1_2_3_EEG_set1.zip?dl=0
$endgroup$
– Maxim David
9 mins ago
$begingroup$
Hmm, I added one more layer and now the accuracy is 100%. I'm not sure the result is correct.
$endgroup$
– Maxim David
7 mins ago
$begingroup$
Could you provide a bit of context for the problem. Are your classes ordered or are they independent? Are you passing the label as an integer or is it one-hot encoded? I'm asking these questions because from what I can see, for example for class no. 3, your model is predicting the nearest classes (i.e. 2 and 4).
$endgroup$
– Djib2011
36 mins ago
$begingroup$
Could you provide a bit of context for the problem. Are your classes ordered or are they independent? Are you passing the label as an integer or is it one-hot encoded? I'm asking these questions because from what I can see, for example for class no. 3, your model is predicting the nearest classes (i.e. 2 and 4).
$endgroup$
– Djib2011
36 mins ago
$begingroup$
You can't always assume that your results would lead to 100% accuracy. With no context, I can only suspect that the differentiation between those 2 particular classes, with all other classes, is weak. Also, maybe they are minority classes and your model is ignoring them. You need to provide some more insight into your data.
$endgroup$
– Sterls
21 mins ago
$begingroup$
You can't always assume that your results would lead to 100% accuracy. With no context, I can only suspect that the differentiation between those 2 particular classes, with all other classes, is weak. Also, maybe they are minority classes and your model is ignoring them. You need to provide some more insight into your data.
$endgroup$
– Sterls
21 mins ago
$begingroup$
the classes are ordered, and label is one-hot encoded.
$endgroup$
– Maxim David
10 mins ago
$begingroup$
the classes are ordered, and label is one-hot encoded.
$endgroup$
– Maxim David
10 mins ago
$begingroup$
Here's the link of data dropbox.com/s/a4ea6t7m102b0j8/person1_2_3_EEG_set1.zip?dl=0
$endgroup$
– Maxim David
9 mins ago
$begingroup$
Here's the link of data dropbox.com/s/a4ea6t7m102b0j8/person1_2_3_EEG_set1.zip?dl=0
$endgroup$
– Maxim David
9 mins ago
$begingroup$
Hmm, I added one more layer and now the accuracy is 100%. I'm not sure the result is correct.
$endgroup$
– Maxim David
7 mins ago
$begingroup$
Hmm, I added one more layer and now the accuracy is 100%. I'm not sure the result is correct.
$endgroup$
– Maxim David
7 mins ago
add a comment |
0
active
oldest
votes
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
);
);
Maxim David is a new contributor. Be nice, and check out our Code of Conduct.
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%2f49800%2fdeep-learning-not-classify-some-classes%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
Maxim David is a new contributor. Be nice, and check out our Code of Conduct.
Maxim David is a new contributor. Be nice, and check out our Code of Conduct.
Maxim David is a new contributor. Be nice, and check out our Code of Conduct.
Maxim David is a new contributor. Be nice, and check out our Code of Conduct.
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%2f49800%2fdeep-learning-not-classify-some-classes%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
$begingroup$
Could you provide a bit of context for the problem. Are your classes ordered or are they independent? Are you passing the label as an integer or is it one-hot encoded? I'm asking these questions because from what I can see, for example for class no. 3, your model is predicting the nearest classes (i.e. 2 and 4).
$endgroup$
– Djib2011
36 mins ago
$begingroup$
You can't always assume that your results would lead to 100% accuracy. With no context, I can only suspect that the differentiation between those 2 particular classes, with all other classes, is weak. Also, maybe they are minority classes and your model is ignoring them. You need to provide some more insight into your data.
$endgroup$
– Sterls
21 mins ago
$begingroup$
the classes are ordered, and label is one-hot encoded.
$endgroup$
– Maxim David
10 mins ago
$begingroup$
Here's the link of data dropbox.com/s/a4ea6t7m102b0j8/person1_2_3_EEG_set1.zip?dl=0
$endgroup$
– Maxim David
9 mins ago
$begingroup$
Hmm, I added one more layer and now the accuracy is 100%. I'm not sure the result is correct.
$endgroup$
– Maxim David
7 mins ago