References
- Abraham R, Marsden J. Foundations of Mechanics. Benjamin Cummings, London 1978
- Atick J, Redlich A. Towards a theory of early visual processing. Neural Comput. 1990; 2: 308–20
- Atick J, Redlich A. What does the retina know about natural scenes. Neural Comput. 1992; 4: 196–210
- Baldi P, Hornik K. Neural networks and principal component analysis: learning from examples without local minima. Neural Networks 1989; 2: 53–8
- Barlow H. Sensory mechanism, the reduction of redundancy, and intelligence. The Mechanisation of Thought Processes. National Physical Laboratory Symp. HMSO, London 1959; 10
- Barlow H. Unsupervised learning. Neural Comput. 1989; 1: 295–311
- Bourlard H, Kamp Y. Auto-association by multilayer perceptron and singular value decomposition. Biol. Cybern. 1988; 58: 291–4
- Burel G. Blind separation of sources: a nonlinear neural algorithm. Neural Networks 1992; 5: 937–47
- Comon P. Independent component analysis, a new concept. Signal Processing 1994; 36: 287–317
- Comon P, Jutten C, Herault J. Blind separation of sources, part II: problem statement. Signal Proc. 1991; 24: 11–20
- Deco G, Brauer W. Higher order statistical decorrelation by volume conserving nonlinear maps. Neural Networks 1994, submitted
- Deco G, Parra L. Nonlinear feature extraction by redundancy reduction with stochastic neural networks. Biol. Cybern. 1994, submitted
- Deco G, Schürman B. Learning time series evolution by unsupervised extraction of correlations. Phys. Rev. E 1994, submitted
- Duda R, Hart P. Pattern Classification and Scene Analysis. Wiley, New York 1973
- Feng K, Qin M-z. The symplectic methods for the computation of Hamiltonian equations. Partial Differential Equations, Zhu You-lan, Guo Ben-yu. Springer, Berlin 1985; 1–35, (Lecture Notes in Mathematics 1297)
- Földiák P. Adaptive network for optimal linear feature extraction. Proc. IEEE/INNS Int. Joint Conf. on Neural Networks, Washington, DC. IEEE Press, Piscataway, NJ 1989; 1: 401–5
- Hastie T, Stuetzle W. Principal curves. J. Am. Stat. Assoc. 1989; 84(406)502–16
- Hornik K, Stinchcombe M, White H. Multilayer feedforward neural networks are universal approximators. Neural Networks 1989; 2: 359–66
- Karhunen J, Joutsensalo J. Prepresentation and separation of signal using nonlinear PCA type learning. Neural Networks 1994; 7: 113–27
- Kuehnel H, Tavan P. The anti-Hebb rule derived from information theory. Parallel Processing in Neural Systems and Computers, R Eckmiller, et al. North-Holland, Amsterdam 1990; 187–90
- Linsker R. Self-organization in a perceptual network. Computer 1988; 21: 105
- Miesbach S, Pesch H. Symplectic phase flow approximation for the numerical integration of canonical systems. Numerical Mathematics 1992; 61: 501–21
- Obradovic D, Deco G. Generalized linear features extraction: an information theory approach. Neural Comput. 1993, submitted
- Oja E. Neural networks, principal components, and subspaces. Int. J. Neural Systems 1989; 1: 61–8
- Papoulis A. Probability, Random Variables, and Stochastic Procl esses3rd edn. McGraw-Hill, New York 1991
- Redlich A. Redundancy reduction as a strategy for unsupervised learning. Neural Comput. 1993a; 5: 289–304
- Redlich A. Supervised factorial learning. Neural Comput. 1993b; 5: 750–66
- Rubner J, Tavan P. A self-organization network for principal-component analysis. Europhys. Lett. 1989; 10: 693–8
- Shannon. A mathematical theory of communication. Bell Sys. Tech. J. 1948; 27: 379–423; 623–56
- Siegel C. Symplectic geometry. Am. J. Math. 1943; 65: 1–86
- Stoer J, Bulirsch R. Introduction to Numerical Analysis. Springer, New York 1993
- Taylor J, Coombes S. Learning higher order correlations. Neural Networks 1993; 6: 423–27