# Kalman Filtering and Neural Networks P5

## DUAL EXTENDED KALMAN FILTER METHODS Eric A. Wan and Alex T. Nelson Department of Electrical and Computer Engineering, Oregon Graduate Institute of Science and Technology, Beaverton, Oregon, . INTRODUCTION The Extended Kalman Filter (EKF) provides an efﬁcient method for generating approximate maximum-likelihood estimates of the state of a discrete-time nonlinear dynamical system (see Chapter 1). The ﬁlter involves a recursive procedure to optimally combine noisy observations with predictions from the known dynamic model. A second use of the EKF involves estimating the parameters of a model (., neural network) given clean training data of input and output data (see Chapter 2). In. | Kalman Filtering and Neural Networks Edited by Simon Haykin Copyright 2001 John Wiley Sons Inc. ISBNs 0-471-36998-5 Hardback 0-471-22154-6 Electronic 5 DUAL EXTENDED KALMAN FILTER METHODS Eric A. Wan and Alex T. Nelson Department of Electrical and Computer Engineering Oregon Graduate Institute of Science and Technology Beaverton Oregon . INTRODUCTION The Extended Kalman Filter EKF provides an efficient method for generating approximate maximum-likelihood estimates of the state of a discrete-time nonlinear dynamical system see Chapter 1 . The filter involves a recursive procedure to optimally combine noisy observations with predictions from the known dynamic model. A second use of the EKF involves estimating the parameters of a model . neural network given clean training data of input and output data see Chapter 2 . In this case the EKF represents a modified-Newton type of algorithm for on-line system identification. In this chapter we consider the dual estimation problem in which both the states of the dynamical system and its parameters are estimated simultaneously given only noisy observations. 123 124 5 DUAL EXTENDED KALMAN FILTER METHODS To be more specific we consider the problem of learning both the hidden states xk and parameters w of a discrete-time nonlinear dynamical system Xk 1 - F Xk Uk w vk 5 yk- H xk w nk where both the system states xk and the set of model parameters w for the dynamical system must be simultaneously estimated from only the observed noisy signal yk. The process noise vk drives the dynamical system observation noise is given by nk and Uk corresponds to observed exogenous inputs. The model structure F - and H - may represent multilayer neural networks in which case w are the weights. The problem of dual estimation can be motivated either from the need for a model to estimate the signal or in other applications from the need for good signal estimates to estimate the model. In general applications can be divided into the tasks

TÀI LIỆU LIÊN QUAN
9    206    0
31    1173    49
1    914    80
89    258    13
80    341    33
51    286    10
95    398    39
16    10    4
47    31    2
1    455    20
TÀI LIỆU XEM NHIỀU
13    39565    2293
3    24053    245
25    23399    4213
16    19374    2824
20    18910    1535
1    18573    604
14    18188    2909
37    15358    2942
3    14741    310
1    13089    116
TỪ KHÓA LIÊN QUAN
TÀI LIỆU MỚI ĐĂNG
65    125    20    29-11-2023
8    47    1    29-11-2023
6    281    3    29-11-2023
64    48    2    29-11-2023
3    99    2    29-11-2023
21    52    1    29-11-2023
9    48    1    29-11-2023
4    44    1    29-11-2023
4    36    1    29-11-2023
124    48    1    29-11-2023
4    59    1    29-11-2023
145    53    10    29-11-2023
155    100    6    29-11-2023
54    48    4    29-11-2023
46    115    3    29-11-2023
8    42    1    29-11-2023
1    381    1    29-11-2023
3    95    2    29-11-2023
7    101    1    29-11-2023
68    51    4    29-11-2023
TÀI LIỆU HOT
3    24053    245
13    39565    2293
3    2262    81
580    4496    361
584    2815    96
62    6028    1
171    5254    710
2    2567    78
51    3934    193
53    4300    187
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.