Sparse representation learning of data by autoencoders with L1/2 regularization

Title:

Sparse representation learning of data by autoencoders with L1/2 regularization

Creator:

Li, Feng , Zurada, Jacek M., and Wu, Wei

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:c12ea2c4-a177-40b0-8018-ca02f7dfa2f3
uuid:c12ea2c4-a177-40b0-8018-ca02f7dfa2f3
doi:10.14311/NNW.2018.28.008

Subject:

autoencoder, sparse representation, unsupervised feature learning, deep network, and L1/2 regularization

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

Autoencoder networks have been demonstrated to be effcient for unsupervised learning of representation of images, documents and time series. Sparse representation can improve the interpretability of the input data and the generalization of a model by eliminating redundant features and extracting the latent structure of data. In this paper, we use L1/2 regularization method to enforce sparsity on the hidden representation of an autoencoder for achieving sparse representation of data. The performance of our approach in terms of unsupervised feature learning and supervised classiffcation is assessed on the MNIST digit data set, the ORL face database and the Reuters-21578 text corpus. The results demonstrate that the proposed autoencoder can produce sparser representation and better reconstruction performance than the Sparse Autoencoder and the L1 regularization Autoencoder. The new representation is also illustrated to be useful for a deep network to improve the classiffcation performance.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2018 Volume:28 | Number:2

Harvested from:

CDK

Metadata only:

false