Abstract
Introduced is some formalism of information geometry, new domain relating differential geometry to probability theory. Analysis and examinations of structure of some special spaces called statistical manifolds have been done. For the new geometry, covariant properties have been introduced. For that the new formalism the so-called α-geometry provides natural interpretation for the learning process, the learning rules have been discussed. The Boltzmann machine is studied using the previously described analysis of the manifold.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
E. Aarts and J. Korst, Simulated Annealing and Boltzmann Machines. A Stochastic Approach to Combinatorial Optimization and Neural Computing, J. Wiley and sons, 1989.
D. Ackley D., G. Hilton and T. Sejnowski, A learning algorithm for Boltzmann machine, Cognitive Science, 9 (1985), 147–169.
S.-I. Amari, Differential Geometrical Methods in Statistics, Lecture Notes in Statistics 28, Springer-Verlag, (1985).
S.-I. Amari, Differential Geometrical Theory of Statistics-Towards New Developments in: S. S. Gupta, Ed., Differential Geometry Statistical Inference, IMS Lecture Notes-Monographs Series, 10 (1987), 19–94.
S.-I. Amari, Information geometry of Boltzmann machine, IEEE Transactions on Neural Networks, 37 (1992), 260–271.
S.-I. Amari, Information geometry, Contemporary Mathematics, 203 (1997), 81–95.
B. Apolloni and D. De Falco, Learning by parallel Boltzmann machines, IEEE Transactions on Information Theory, 37 (4) (1991), 1162–1165.
R. Azencott, Boltzmann machines: Higher-order interactions and synchronous learning in: Stochastic Models, Statistical Methods, and Algorithms in Image Analysis, Proc. Spec. Year Image Anal., Rome (Italy) 1990, Lect. Notes Stat., 74 (1992), 14–45.
G. Burdet, α-Divergence sur les variétés statistiques, preprint, Centre de Physique Théorique, 1995.
G. Burdet, H. Nencka and M. Perrin, An Exemple of Dynamical Behaviour of the Relative Entropy, Contemporary Mathematics, 203 (1997), 97–104.
G. Burdet and M. Perrin, Conformal implementation of the projective equivalence over statistical manifolds, Indag. Math., N.S., 8, (1997), 7–17.
N. N. Chentsov, Statistical Decision and Optimal Inference, Nauka, Moscow, 1972 (in Russian); translation in English, American Mathematical Society, Providence, R.I., 53 (1982).
Ph. Combe and H. Nencka, Information Geometry and Learning in Formal Neural Networks, Contemporary Mathematics, 203 (1997), 105–116.
H. Cramér, Mathematical Methods of Statistics, Princeton University Press, 1946.
I. Csiszár, I-divergence geometry of probability distributions and minimization problems, Ann. of Probab., 3 (1975), 146–158.
I. Csiszár and J. Körner, Information Theory, Academic Press, 1981.
A. P. Dawid, Discussion on Pr. Efron’s paper (1975), Ann. Statist., 3 (1975), 1231–1234.
A. P. Dawid, Further comments on some comments on a paper by Bradley Efron, Ann. Statist., 5 (1977), 1249.
B. Efron, Defining the curvature of a statistical problem, Ann. Stat., 3 (1975), 1189–1217.
B. Efron, The geometry of exponential families, Ann. Stat., 6 (1978), 362–376.
R. A. Fisher, Theory of statistical estimation, Proc. Camb. Phil. Soc., 22 (1925), 700–725
S. Kullback, Information Theory and Statistics, Wiley, New York, 1959.
S. Kullback and R. Leibler, On information and sufficiency, Ann. Math. Stat., 22 (1951), 79–86.
C. R. Rao, Information and the accuracy attainable in the estimation of statistical parameters, Bull. Calcutta Math. Soc., 37 (1945), 81–91.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer Basel AG
About this paper
Cite this paper
Burdet, G., Combe, P., Nencka, H. (1999). Statistical Manifolds, Self-Parallel Curves and Learning Processes. In: Dalang, R.C., Dozzi, M., Russo, F. (eds) Seminar on Stochastic Analysis, Random Fields and Applications. Progress in Probability, vol 45. Birkhäuser, Basel. https://doi.org/10.1007/978-3-0348-8681-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-0348-8681-9_7
Publisher Name: Birkhäuser, Basel
Print ISBN: 978-3-0348-9727-3
Online ISBN: 978-3-0348-8681-9
eBook Packages: Springer Book Archive