Abstract | ||
---|---|---|
In this work we propose an l(p)-norm data fidelity constraint for training the autoencoder. Usually the Euclidean distance is used for this purpose; we generalize the l(2)-norm to the l(p)-norm; smaller values of p make the problem robust to outliers. The ensuing optimization problem is solved using the Augmented Lagrangian approach. The proposed l(p)-norm Autoencoder has been tested on benchmark deep learning datasets - MNIST, CIFAR-10 and SVHN. We have seen that the proposed robust autoencoder yields better results than the standard autoencoder (l(2)-norm) and deep belief network for all of these problems. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-46675-0_66 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Autoencoder,Deep learning,Classification,Robust estimation | Autoencoder,MNIST database,Pattern recognition,Computer science,Deep belief network,Euclidean distance,Outlier,Augmented Lagrangian method,Artificial intelligence,Deep learning,Optimization problem | Conference |
Volume | ISSN | Citations |
9949 | 0302-9743 | 1 |
PageRank | References | Authors |
0.36 | 9 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Janki Mehta | 1 | 3 | 0.71 |
Kavya Gupta | 2 | 1 | 0.36 |
Anupriya Gogna | 3 | 123 | 9.90 |
A. Majumdar | 4 | 644 | 75.83 |
Saket Anand | 5 | 87 | 9.36 |