References
- Barlow H B. Unsupervised learning. Neural Comput. 1989; 1: 295–311
- Bell A J, Sejnowski T J. The ‘independent components’ of natural scenes are edge filters. Vision Res 1997, submitted
- CEDAR. USPS Office of Advanced Technology database of handwritten cities, states, ZIP codes, digits, and alphabetic characters. Center of Excellence for Document Analysis and Recognition Image Database. 1992; 1, CD-ROM
- Dayan P, Hinton G E. Varieties of Helmholtz machine. Neural Networks 1996; 9: 1385–403
- Field D J. What is the goal of sensory coding?. Neural Comput. 1994; 6: 559–601
- Foldiak P. Forming sparse representations by local anti-Hebbian learning. Biol. Cybern. 1990; 64: 165–70
- Friedman J H, Tukey J W. A projection pursuit algorithm for exploratory data analysis. IEEE Trans. Comput. 1974; C-23: 881–90
- Hebb D O. The Organisation of Behavior. Wiley, New York 1949
- Hinton G E, Dayan P, Frey B J, Neal R M. The wake-sleep algorithm for unsupervised neural networks. Science 1995; 268: 1158–61
- Hinton G E, Zemel R. Autoencoders, minimum description-length and Helmholtz free energy. Advances in Neural Information Processing Systems 6, J Cowan, G Tesauro, J Alspector. Morgan Kaufman, San Mateo, CA 1994; 3–10
- Lee D D, Seung H S. Unsupervised learning by convex and conic coding. Advances in Neural Information Processing Systems 9. MIT Press, Cambridge, MA 1997; 515–21
- Luttrell S P. Designing analysable networks. Handbook of Neural Computation. Oxford University Press, Oxford 1995
- Luttrell S P. A unified model of density models and auto-encoders. Preprint NI97039-NNM. Isaac Newton Institute. 1997, obtainable from http://www.newton.cam.ac.uk/preprints.html
- Luttrell S P. A Bayesian analysis of complementary approaches to training self-organising stochastic networks. Technical Report DERA/CIS/CIS5/TR97165. Information Centre, DERA, Malvern, UK 1998
- Oja E. A simplified neuron model as a principal component analyser. J. Math. Biol. 1982; 15: 267–73
- Olshausen B A, Field D J. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 1996; 381: 607–9
- Olshausen B A, Field D J. Sparse coding with an overcomplete basis set: a strategy employed by V1?. Vision Res. 1997; 37: 3311–25
- Saund E. A multiple cause mixture model for unsupervised learning. Neural Comput. 1995; 7: 57–71
- Webber C J S. Self-organisation of position- and deformation-tolerant neural representations. Network: Comput. Neural Syst. 1991; 2: 43–61
- Webber C J S. Self-organisation of transformation-invariant detectors for constituents of perceptual patterns. Network: Comput. Neural Syst. 1994; 5: 471–96
- Webber C J S. Generalisation and discrimination emerge from a self-organising componential network: a speech example. Network: Comput. Neural Syst. 1997; 8: 425–40
- Webber C J S. Self-organisation of symmetry networks. Neural Comput. 1998, submitted
- Zemel R. A minimum description-length framework for unsupervised learning. PhD Thesis. University of Toronto. 1993