Online Learning of Riemannian Hidden Markov Models in Homogeneous Hadamard Spaces

被引：4

作者：

Tupker, Quinten ^{[1
]}

Said, Salem ^{[2
]}

Mostajeran, Cyrus ^{[3
]}

机构：

[1] Ctr Math Sci, Wilberforce Rd, Cambridge CB3 0WA, England

[2] Univ Bordeaux, CNRS, Bordeaux, France

[3] Univ Cambridge, Dept Engn, Cambridge CP2 1PZ, England

来源：

GEOMETRIC SCIENCE OF INFORMATION (GSI 2021) | 2021年 / 12829卷

基金：

欧洲研究理事会;

关键词：

Hidden Markov model; Riemannian manifold; Gaussian distribution; Expectation-maximization; k-means clustering; Stochastic gradient descent;

D O I：

10.1007/978-3-030-80209-7_5

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Hidden Markov models with observations in a Euclidean space play an important role in signal and image processing. Previous work extending to models where observations lie in Riemannian manifolds based on the Baum-Welch algorithm suffered from high memory usage and slow speed. Here we present an algorithm that is online, more accurate, and offers dramatic improvements in speed and efficiency.

引用

页码：37 / 44

页数：8

共 11 条

[1] Multiclass Brain-Computer Interface Classification by Riemannian Geometry
Barachant, Alexandre
Bonnet, Stephane
Congedo, Marco
Jutten, Christian
[J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2012, 59 (04) : 920 - 928
[2] Computing the Karcher mean of symmetric positive definite matrices
Bini, Dario A.
Iannazzo, Bruno
[J]. LINEAR ALGEBRA AND ITS APPLICATIONS, 2013, 438 (04) : 1700 - 1710
[3] BAUM FORWARD - BACKWARD ALGORITHM REVISITED
DEVIJVER, PA
[J]. PATTERN RECOGNITION LETTERS, 1985, 3 (06) : 369 - 373
[4] Heuveline S., 2021, ARXIV PREPRINT ARXIV
[5] THE KAHLER MEAN OF BLOCK-TOEPLITZ MATRICES WITH TOEPLITZ STRUCTURED BLOCKS
Jeuris, B.
Vandebril, R.
[J]. SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2016, 37 (03) : 1151 - 1175
[6] ONLINE ESTIMATION OF HIDDEN MARKOV MODEL PARAMETERS BASED ON THE KULLBACK-LEIBLER INFORMATION MEASURE
KRISHNAMURTHY, V
MOORE, JB
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1993, 41 (08) : 2557 - 2573
[7] A Riemannian framework for tensor computing
Pennec, X
Fillard, P
Ayache, N
[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2006, 66 (01) : 41 - 66
[8] A TUTORIAL ON HIDDEN MARKOV-MODELS AND SELECTED APPLICATIONS IN SPEECH RECOGNITION
RABINER, LR
[J]. PROCEEDINGS OF THE IEEE, 1989, 77 (02) : 257 - 286
[9] Said S., ARXIV PREPRINT ARXIV
[10] Riemannian Gaussian Distributions on the Space of Symmetric Positive Definite Matrices
Said, Salem
Bombrun, Lionel
Berthoumieu, Yannick
Manton, Jonathan H.
[J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2017, 63 (04) : 2153 - 2170

← 1 2 →