Non-negative Matrix Factorization with Sparseness Constraints
The Journal of Machine Learning Research
A fast learning algorithm for deep belief nets
Neural Computation
Face recognition using localized features based on non-negative sparse coding
Machine Vision and Applications
Learning Image Components for Object Recognition
The Journal of Machine Learning Research
Exploring Strategies for Training Deep Neural Networks
The Journal of Machine Learning Research
Detect and track latent factors with online nonnegative matrix factorization
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Online Learning for Matrix Factorization and Sparse Coding
The Journal of Machine Learning Research
Hi-index | 0.00 |
We present an efficient online learning scheme for non-negative sparse coding in autoencoder neural networks. It comprises a novel synaptic decay rule that ensures non-negative weights in combination with an intrinsic self-adaptation rule that optimizes sparseness of the non-negative encoding. We show that non-negativity constrains the space of solutions such that overfitting is prevented and very similar encodings are found irrespective of the network initialization and size. We benchmark the novel method on real-world datasets of handwritten digits and faces. The autoencoder yields higher sparseness and lower reconstruction errors than related offline algorithms based on matrix factorization. It generalizes to new inputs both accurately and without costly computations, which is fundamentally different from the classical matrix factorization approaches.