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 2 days ago
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 2 days ago
Albert
1
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
2 days ago
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 2 days ago
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 2 days ago
Albert
1
asked 2 days ago
Albert
1
asked 2 days ago
Albert
1
asked 2 days ago
Albert
1
asked 2 days ago
Albert
1
1
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
2 days ago
add a comment |
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
2 days ago
1
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
2 days ago
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
2 days ago
add a comment |
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
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
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
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
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
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
1
This is completely normal, and its due to the random weight initialization.
– Matias Valdenegro
2 days ago