search

ivan-vasilev / neuralnetworks

java deep learning algorithms and deep neural networks with gpu acceleration
1.23k stars 361 forks source link

Is it possible to implement sparse autoencoder with your lib? #29

Open dims12 opened 10 years ago

dims12 commented 10 years ago

Sparse autoencoder is an autoencoder with additional constraint that most coefficients tend to be zero, as described here: http://deeplearning.stanford.edu/wiki/index.php/Autoencoders_and_Sparsity

Is it possible to implement and train such a net with your lib?

ivan-vasilev commented 10 years ago

It wouldn't be a problem to implement it, but it's not available at the moment. I can try to do it, but I'm not able to give you a specific time frame for completion. But if you'd like to contribute you are more than welcome and I'll assist in any way possible. Thanks.

On Mon, Jun 23, 2014 at 12:35 AM, dims12 notifications@github.com wrote:

Sparse autoencoder is an autoencoder with additional constraint that most coefficients tend to be zero, as described here: http://deeplearning.stanford.edu/wiki/index.php/Autoencoders_and_Sparsity

Is it possible to implement and train such a net with your lib?

— Reply to this email directly or view it on GitHub https://github.com/ivan-vasilev/neuralnetworks/issues/29.