Competitive learning algorithms for vector quantization
Neural Networks
A multiple cause mixture model for unsupervised learning
Neural Computation
Self-organizing maps
A Neural Network for PCA and Beyond
Neural Processing Letters
A simple algorithm that discovers efficient perceptual codes
Computational and psychophysical mechanisms of visual coding
Sparse coding in the primate cortex
The handbook of brain theory and neural networks
Feature extraction through LOCOCODE
Neural Computation
Learning the parts of objects by auto-association
Neural Networks
Preintegration lateral inhibition enhances unsupervised learning
Neural Computation
Local Non-Negative Matrix Factorization as a Visual Representation
ICDL '02 Proceedings of the 2nd International Conference on Development and Learning
Learning with mixtures of trees
The Journal of Machine Learning Research
Non-negative matrix factorization based methods for object recognition
Pattern Recognition Letters
Non-negative Matrix Factorization with Sparseness Constraints
The Journal of Machine Learning Research
Competition and multiple cause models
Neural Computation
Neural coding strategies and mechanisms of competition
Cognitive Systems Research
Nonnegative matrix factorization with quadratic programming
Neurocomputing
Maximal Causes for Non-linear Component Extraction
The Journal of Machine Learning Research
Pattern Discovery for High-Dimensional Binary Datasets
Neural Information Processing
Blind Image Separation Using Nonnegative Matrix Factorization with Gibbs Smoothing
Neural Information Processing
Computational Intelligence and Neuroscience - Advances in Nonnegative Matrix and Tensor Factorization
Unsupervised learning of overlapping image components using divisive input modulation
Computational Intelligence and Neuroscience
Recurrent-neural-network-based Boolean factor analysis and its application to word clustering
IEEE Transactions on Neural Networks
Bars problem solving - new neural network method and comparison
MICAI'07 Proceedings of the artificial intelligence 6th Mexican international conference on Advances in artificial intelligence
Generalized softmax networks for non-linear component extraction
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
PReMI'07 Proceedings of the 2nd international conference on Pattern recognition and machine intelligence
Expectation Truncation and the Benefits of Preselection In Training Generative Models
The Journal of Machine Learning Research
Non-monotone projection gradient method for non-negative matrix factorization
Computational Optimization and Applications
Multistability of α-divergence based NMF algorithms
Computers & Mathematics with Applications
Solving non-negative matrix factorization by alternating least squares with a modified strategy
Data Mining and Knowledge Discovery
Modified subspace Barzilai-Borwein gradient method for non-negative matrix factorization
Computational Optimization and Applications
Global Minima Analysis of Lee and Seung's NMF Algorithms
Neural Processing Letters
Hi-index | 0.00 |
In order to perform object recognition it is necessary to learn representations of the underlying components of images. Such components correspond to objects, object-parts, or features. Non-negative matrix factorisation is a generative model that has been specifically proposed for finding such meaningful representations of image data, through the use of non-negativity constraints on the factors. This article reports on an empirical investigation of the performance of non-negative matrix factorisation algorithms. It is found that such algorithms need to impose additional constraints on the sparseness of the factors in order to successfully deal with occlusion. However, these constraints can themselves result in these algorithms failing to identify image components under certain conditions. In contrast, a recognition model (a competitive learning neural network algorithm) reliably and accurately learns representations of elementary image features without such constraints.