The “independent components” of natural scenes are edge filters

Amari, 1996, A new learning algorithm for blind signal separation, Vol. 8

Atick, 1992, Could information theory provide an ecological theory of sensory processing?, Network, 3, 213, 10.1088/0954-898X/3/2/009

Atick, 1990, Towards a theory of early visual processing, Neural Computation, 2, 308, 10.1162/neco.1990.2.3.308

Atick, 1993, Convergent algorithm for sensory receptive field development, Neural Computation, 5, 45, 10.1162/neco.1993.5.1.45

Baddeley, 1996, Searching for filters with “interesting” output distributions: an uninteresting direction to explore?, Network, 10.1088/0954-898X/7/2/021

Barlow, 1989, Unsupervised learning, Neural Computation, 1, 295, 10.1162/neco.1989.1.3.295

Barlow, 1994, What is the computational goal of the neocortex?

Barlow, 1992, Why do you have edge detectors?, Optical Society of America: Technical Digest, 23, 172

Bell, 1992, Self-organisation in real neurons: anti-Hebb in channel space?, Vol. 4, 59

Bell, 1995, An information maximization approach to blind separation and blind deconvolution, Neural Computation, 7, 1129, 10.1162/neco.1995.7.6.1129

Bell, 1995, Fast blind separation based on information theory

Bell, 1996, Learning the higher-order structure of a natural sound, Network: Computation in Neural Systems, 7, 2, 10.1088/0954-898X/7/2/005

Bialek, 1991, Optimal sampling of natural images: a design principle for the visual system?, Vol. 1

Bienenstock, 1982, Theory for the development of neuron selectivity: orientation specificity and binocular interaction in visual cortex, Journal of Neuroscience, 21, 32, 10.1523/JNEUROSCI.02-01-00032.1982

Burr, 1990, Feature detection in biological and artificial vision systems

Cardoso, 1996, Equivariant adaptive source separation

Cichocki, 1994, Robust learning algorithm for blind separation of signals, Electronics Letters, 3017, 1386, 10.1049/el:19940956

Comon, 1994, Independent component analysis, a new concept?, Signal Processing, 36, 287, 10.1016/0165-1684(94)90029-9

Cover, 1991

Daugman, 1985, Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters, Journal of the Optical Society of America A, 27, 1160, 10.1364/JOSAA.2.001160

Ferster, 1996, Orientation selectivity of thalamic input to simple cells of cat visual cortex, Nature, 380, 249, 10.1038/380249a0

Field, 1987, Relations between the statistics of natural images and the response properties of cortical cells, Journal of the Optical Society of America A, 412, 2370

Field, 1994, What is the goal of sensory coding?, Neural Computation, 6, 559, 10.1162/neco.1994.6.4.559

Földiák, 1990, Forming sparse representations by local antiHebbian learning, Biological Cybernetics, 64, 165, 10.1007/BF02331346

Fyfe, 1995, Finding compact and sparsedistributed representations of visual images, Network, 6, 333, 10.1088/0954-898X/6/3/002

Goodall, 1960, Performance of stochastic net, Nature, 185, 557, 10.1038/185557a0

Hancock, 1992, The principal components of natural images, Network, 3, 61, 10.1088/0954-898X/3/1/008

Harpur, 1996, Development of low entropy coding in a recurrent network, Network, 10.1088/0954-898X/7/2/007

1994

Hubel, 1968, Receptive fields and functional architecture of monkey striate cortex, Journal of Physiology, 195, 215, 10.1113/jphysiol.1968.sp008455

Hubel, 1974, Uniformity of monkey striate cortex: a parallel relationship between field size, scatter, and magnification factor, Journal of Comparative Neurology, 158, 295, 10.1002/cne.901580305

Huber, 1985, Projection pursuit, The Annals of Statistics, 13, 435, 10.1214/aos/1176349519

Intrator, 1992, Feature extraction using an unsupervised neural network, Neural Computation, 4, 98, 10.1162/neco.1992.4.1.98

Jutten, 1991, Blind separation of sources, Part I: an adaptive algorithm based on neuromimetic architecture, Signal Processing, 24, 1, 10.1016/0165-1684(91)90079-X

Karhunen, 1995, Neural estimation of basis vectors in Independent Component Analysis

Karhunen, 1996, A class of neural networks for independent component analysis, IEEE Trans. on Neural Networks

Laughlin, 1981, A simple coding procedure enhances a neuron's information capacity, Z. Naturforsch., 36, 910, 10.1515/znc-1981-9-1040

Law, 1994, Formation of receptive fields in realistic visual environments according to the Bienestock, Cooper and Munro (BCM) theory, 91, 7797

Lee, 1997, Blind separation of delayed and convolved sources, Vol. 9

Linsker, 1992, Local synaptic learning rules suffice to maximise mutual information in a linear network, Neural Computation, 4, 691, 10.1162/neco.1992.4.5.691

Linsker, 1988, Self-organization in a perceptual network, Computer, 21, 105, 10.1109/2.36

Marr, 1980, Theory of edge detection, 207, 187

Miller, 1988, Correlation-based models of neural development, 267

Nadal, 1994, Non-linear neurons in the low noise limit: a factorial code maximises information transfer, Network, 5, 565, 10.1088/0954-898X/5/4/008

Oja, 1989, Neural networks, principal components and linear neural networks, Neural Networks, 5, 927, 10.1016/S0893-6080(05)80089-9

Olshausen, 1996, Learning linear, sparse, factorial codes

Olshausen, 1996, Natural image statistics and efficient coding, Network: Computation in Neural Systems, 7, 2, 10.1088/0954-898X/7/2/014

Pham, 1992, Separation of a mixture of independent sources through a maximum likelihood approach, 771

Ruderman, 1994, The statistics of natural images, Network: Computation in Neural Systems, 5, 517, 10.1088/0954-898X/5/4/006

Sanger, 1989, Optimal unsupervised learning in a single-layer network, Neural Networks, 2, 459, 10.1016/0893-6080(89)90044-0

Schmidhuber, 1996, Semi-linear predictability minimization produces well-known feature detectors, Neural Computation, 10.1162/neco.1996.8.4.773

Shouval, 1995, Formation and organisation of receptive fields, with an input environment composed of natural scenes

Torkkola, 1996, Blind separation of convolved sources based on information maximisation

van Hateren, 1992, A theory of maximising sensory information, Biol. Cybern., 68, 23, 10.1007/BF00203134