Learning Overcomplete Representations
Top Cited Papers
- 1 February 2000
- journal article
- research article
- Published by MIT Press in Neural Computation
- Vol. 12 (2) , 337-365
- https://doi.org/10.1162/089976600300015826
Abstract
In an overcomplete basis, the number of basis vectors is greater than the dimensionality of the input, and the representation of an input is not a unique combination of basis vectors. Overcomplete ...Keywords
This publication has 21 references indexed in Scilit:
- Emergence of simple-cell receptive field properties by learning a sparse code for natural imagesNature, 1996
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- Nonlinear neurons in the low-noise limit: a factorial code maximizes information transferNetwork: Computation in Neural Systems, 1994
- What Is the Goal of Sensory Coding?Neural Computation, 1994
- Matching pursuits with time-frequency dictionariesIEEE Transactions on Signal Processing, 1993
- Shiftable multiscale transformsIEEE Transactions on Information Theory, 1992
- Entropy-based algorithms for best basis selectionIEEE Transactions on Information Theory, 1992
- The wavelet transform, time-frequency localization and signal analysisIEEE Transactions on Information Theory, 1990
- Entropy reduction and decorrelation in visual coding by oriented neural receptive fieldsIEEE Transactions on Biomedical Engineering, 1989
- Complete discrete 2-D Gabor transforms by neural networks for image analysis and compressionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988