Title | ||
---|---|---|
Deep Learning of Part-Based Representation of Data Using Sparse Autoencoders With Nonnegativity Constraints. |
Abstract | ||
---|---|---|
We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (nonnegativity-constrained autoencoder), that learns features that show part-based representation of data. The learning algorithm is based on constraining negative weights. The performance of the algorithm is assessed based on decomposing data into parts and its prediction performance is tested ... |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TNNLS.2015.2479223 | IEEE Transactions on Neural Networks and Learning Systems |
Keywords | Field | DocType |
Training,Feature extraction,Artificial neural networks,Machine learning,Image reconstruction,Encoding,Cost function | Data set,Autoencoder,Pattern recognition,Computer science,Constraint algorithm,Feature extraction,Non-negative matrix factorization,Artificial intelligence,Deep learning,Artificial neural network,Machine learning,Encoding (memory) | Journal |
Volume | Issue | ISSN |
27 | 12 | 2162-237X |
Citations | PageRank | References |
36 | 1.17 | 24 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ehsan Hossaini Asl | 1 | 77 | 8.03 |
Jacek M. Zurada | 2 | 2553 | 226.22 |
Olfa Nasraoui | 3 | 1515 | 164.53 |