Difference in accuracy in FC-DNN on different run
up vote
0
down vote
favorite
I have been facing an issue of instability in deep neural networks. For example, while using DNN with fully connected layers (3 layers, 128 memory units in each), I am having a range of unweighted accuracy of 62% to 66% in the different runs (yes, the same train and test set). I used Xavier initializer and bias initializer as zero. All the other parameters are also fixed.
Have anyone faced such problems? I have tried to use fixed seed too, but it doesn't seem to help. Kinda puzzled about what is creating this instability.
Thanks in advance :)
neural-network deep-learning
asked Nov 10 at 10:06
Albert
1
add a comment |
up vote
0
down vote
favorite
I have been facing an issue of instability in deep neural networks. For example, while using DNN with fully connected layers (3 layers, 128 memory units in each), I am having a range of unweighted accuracy of 62% to 66% in the different runs (yes, the same train and test set). I used Xavier initializer and bias initializer as zero. All the other parameters are also fixed.
Have anyone faced such problems? I have tried to use fixed seed too, but it doesn't seem to help. Kinda puzzled about what is creating this instability.
Thanks in advance :)
neural-network deep-learning
asked Nov 10 at 10:06
Albert
1
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
Nov 10 at 11:34
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
I have been facing an issue of instability in deep neural networks. For example, while using DNN with fully connected layers (3 layers, 128 memory units in each), I am having a range of unweighted accuracy of 62% to 66% in the different runs (yes, the same train and test set). I used Xavier initializer and bias initializer as zero. All the other parameters are also fixed.
Have anyone faced such problems? I have tried to use fixed seed too, but it doesn't seem to help. Kinda puzzled about what is creating this instability.
Thanks in advance :)
neural-network deep-learning
asked Nov 10 at 10:06
Albert
1
I have been facing an issue of instability in deep neural networks. For example, while using DNN with fully connected layers (3 layers, 128 memory units in each), I am having a range of unweighted accuracy of 62% to 66% in the different runs (yes, the same train and test set). I used Xavier initializer and bias initializer as zero. All the other parameters are also fixed.
Have anyone faced such problems? I have tried to use fixed seed too, but it doesn't seem to help. Kinda puzzled about what is creating this instability.
Thanks in advance :)
neural-network deep-learning
neural-network deep-learning
asked Nov 10 at 10:06
Albert
1
asked Nov 10 at 10:06
Albert
1
asked Nov 10 at 10:06
Albert
1
asked Nov 10 at 10:06
Albert
1
asked Nov 10 at 10:06
Albert
1
1
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
Nov 10 at 11:34
add a comment |
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
Nov 10 at 11:34
1
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
Nov 10 at 11:34
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
Nov 10 at 11:34
add a comment |
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- 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.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- 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.
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%2fstackoverflow.com%2fquestions%2f53237890%2fdifference-in-accuracy-in-fc-dnn-on-different-run%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
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
Nov 10 at 11:34