TY - GEN
T1 - Information geometry of statistical inference - An overview
AU - Amari, Shun Ichi
N1 - Publisher Copyright:
© 2002 IEEE.
PY - 2002
Y1 - 2002
N2 - The present paper gives a short introduction to information geometry, by using a simple model of an exponential family which is a dually flat Riemannian space. The paper then overviews some of the applications of information geometry: 1) the higher-order asymptotic theory of estimation; 2) semiparametric estimation of the parameter of interest; 3) learning neural networks under the Riemannian structure; and 4) analysis of turbo codes, low density parity check codes and belief propagation algorithm.
AB - The present paper gives a short introduction to information geometry, by using a simple model of an exponential family which is a dually flat Riemannian space. The paper then overviews some of the applications of information geometry: 1) the higher-order asymptotic theory of estimation; 2) semiparametric estimation of the parameter of interest; 3) learning neural networks under the Riemannian structure; and 4) analysis of turbo codes, low density parity check codes and belief propagation algorithm.
UR - http://www.scopus.com/inward/record.url?scp=84939139946&partnerID=8YFLogxK
U2 - 10.1109/ITW.2002.1115423
DO - 10.1109/ITW.2002.1115423
M3 - 会議への寄与
AN - SCOPUS:84939139946
T3 - Proceedings of the 2002 IEEE Information Theory Workshop, ITW 2002
SP - 86
EP - 89
BT - Proceedings of the 2002 IEEE Information Theory Workshop, ITW 2002
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2002 IEEE Information Theory Workshop, ITW 2002
Y2 - 20 October 2002 through 25 October 2002
ER -