scholarly journals Bootstrapping Neural Networks

2000 ◽  
Vol 12 (8) ◽  
pp. 1929-1949 ◽  
Author(s):  
Jürgen Franke ◽  
Michael H. Neumann
Keyword(s):  
Neural Networks ◽  
Classical Method ◽  
Parameter Estimates ◽  
Model Parameters ◽  
Statistical Estimator ◽  
Consistency Results ◽  
Data Generating Process ◽  
Probabilistic Structure ◽  
Output Space

Knowledge about the distribution of a statistical estimator is important for various purposes, such as the construction of confidence intervals for model parameters or the determination of critical values of tests. A widely used method to estimate this distribution is the so-called bootstrap, which is based on an imitation of the probabilistic structure of the data-generating process on the basis of the information provided by a given set of random observations. In this article we investigate this classical method in the context of artificial neural networks used for estimating a mapping from input to output space. We establish consistency results for bootstrap estimates of the distribution of parameter estimates.

scholarly journals NEURAL NETWORK INVERSION OF RESISTIVITY DATA FOR DETERMINATION OF DISTANCE TO A BED BOUNDARY

2021 ◽  
Vol 2 (2) ◽  
pp. 95-102
Author(s):  
Dmitry Yu. Kushnir ◽  
Nikolay N. Velker ◽  
Darya V. Andornaya ◽  
Yuriy E. Antonov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Estimation ◽  
Model Parameters ◽  
Formation Model ◽  
Inversion Algorithm ◽  
Resistivity Data ◽  
Neural Network Inversion ◽  
Real Time Estimation

Accurate real-time estimation of a distance to the nearest bed boundary simplifies the steering of directional wells. For estimation of that distance, we propose an approach of pointwise inversion of resistivity data using neural networks based on two-layer resistivity formation model. The model parameters are determined from the tool responses using a cascade of neural networks. The first network calculates the resistivity of the layer containing the tool measure point. The subsequent networks take as input the tool responses and the model parameters determined with the previous networks. All networks are trained on the same synthetic database. The samples of that database consist of the pairs of model parameters and corresponding noisy tool responses. The results of the proposed approach are close to the results of the general inversion algorithm based on the method of the most-probable parameter combination. At the same time, the performance of the proposed inversion is several orders faster.

scholarly journals An approach to identify time consistent model parameters: sub-period calibration

2013 ◽  
Vol 17 (1) ◽  
pp. 149-161 ◽  
Author(s):  
S. Gharari ◽  
M. Hrachowitz ◽  
F. Fenicia ◽  
H. H. G. Savenije
Keyword(s):  
Model Performance ◽  
Realistic Model ◽  
Parameter Estimates ◽  
Model Parameters ◽  
New Approach ◽  
Consistent Model ◽  
Set Up ◽  
Consistent Parameter

Abstract. Conceptual hydrological models rely on calibration for the identification of their parameters. As these models are typically designed to reflect real catchment processes, a key objective of an appropriate calibration strategy is the determination of parameter sets that reflect a "realistic" model behavior. Previous studies have shown that parameter estimates for different calibration periods can be significantly different. This questions model transposability in time, which is one of the key conditions for the set-up of a "realistic" model. This paper presents a new approach that selects parameter sets that provide a consistent model performance in time. The approach consists of testing model performance in different periods, and selecting parameter sets that are as close as possible to the optimum of each individual sub-period. While aiding model calibration, the approach is also useful as a diagnostic tool, illustrating tradeoffs in the identification of time-consistent parameter sets. The approach is applied to a case study in Luxembourg using the HyMod hydrological model as an example.

scholarly journals Determination of parameter identifiability in nonlinear biophysical models: A Bayesian approach

2014 ◽  
Vol 143 (3) ◽  
pp. 401-416 ◽  
Author(s):  
Keegan E. Hines ◽  
Thomas R. Middendorf ◽  
Richard W. Aldrich
Keyword(s):  
Biological Molecules ◽  
Parameter Estimates ◽  
Model Parameters ◽  
Biophysical Parameters ◽  
Physical Mechanisms ◽  
Biophysical Models ◽  
Underlying Causes ◽  
True Values ◽  
Accurate Quantification

A major goal of biophysics is to understand the physical mechanisms of biological molecules and systems. Mechanistic models are evaluated based on their ability to explain carefully controlled experiments. By fitting models to data, biophysical parameters that cannot be measured directly can be estimated from experimentation. However, it might be the case that many different combinations of model parameters can explain the observations equally well. In these cases, the model parameters are not identifiable: the experimentation has not provided sufficient constraining power to enable unique estimation of their true values. We demonstrate that this pitfall is present even in simple biophysical models. We investigate the underlying causes of parameter non-identifiability and discuss straightforward methods for determining when parameters of simple models can be inferred accurately. However, for models of even modest complexity, more general tools are required to diagnose parameter non-identifiability. We present a method based in Bayesian inference that can be used to establish the reliability of parameter estimates, as well as yield accurate quantification of parameter confidence.

scholarly journals Moving beyond traditional model calibration or how to better identify realistic model parameters: sub-period calibration

2012 ◽  
Vol 9 (2) ◽  
pp. 1885-1918
Author(s):  
S. Gharari ◽  
M. Hrachowitz ◽  
F. Fenicia ◽  
H. H. G. Savenije
Keyword(s):  
Model Calibration ◽  
Model Performance ◽  
Realistic Model ◽  
Parameter Estimates ◽  
Model Parameters ◽  
New Approach ◽  
Consistent Model ◽  
Set Up

Abstract. Conceptual hydrological models often rely on calibration for the identification of their parameters. As these models are typically designed to reflect real catchment processes, a key objective of an appropriate calibration strategy is the determination of parameter sets that reflect a "realistic" model behavior. Previous studies have shown that parameter estimates for different calibration periods can be significantly different. This questions model transposability in time, which is one of the key conditions for the set-up of a "realistic" model. This paper presents a new approach that selects parameter sets that provide a consistent model performance in time. The approach consists of confronting model performance in different periods, and selecting parameter sets that are as close as possible to the optimum of each individual sub-period. While aiding model calibration, the approach is also useful as a diagnostic tool, illustrating tradeoffs in the identification of time consistent parameter sets. The approach is demonstrated in a case study where we illustrate the multi-objective calibration of the HyMod hydrological model to a Luxembourgish catchment.

Operational Determination of the Activated Sludge Process Using Neural Networks

1992 ◽  
Vol 26 (9-11) ◽  
pp. 2461-2464 ◽  
Author(s):  
R. D. Tyagi ◽  
Y. G. Du
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Steady State ◽  
Activated Sludge ◽  
Feedforward Neural Network ◽  
Training Data ◽  
Activated Sludge Process

A steady-statemathematical model of an activated sludgeprocess with a secondary settler was developed. With a limited number of training data samples obtained from the simulation at steady state, a feedforward neural network was established which exhibits an excellent capability for the operational prediction and determination.

scholarly journals Determination of the geophysical model function of the ERS-1 scatterometer by the use of neural networks

1998 ◽  
Vol 103 (C6) ◽  
pp. 12853-12868 ◽  
Author(s):  
Carlos Mejia ◽  
Sylvie Thiria ◽  
Ngan Tran ◽  
Michel Crépon ◽  
Fouad Badran
Keyword(s):  
Neural Networks ◽  
Model Function ◽  
Geophysical Model ◽  
Geophysical Model Function

Determination of application volume for coffee plantations using artificial neural networks and remote sensing

2021 ◽  
Vol 184 ◽  
pp. 106096
Author(s):  
Mailson Freire de Oliveira ◽  
Adão Felipe dos Santos ◽  
Elizabeth Haruna Kazama ◽  
Glauco de Souza Rolim ◽  
Rouverson Pereira da Silva
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Coffee Plantations ◽  
Artificial Neural ◽  
Application Volume

scholarly journals Application of Artificial Neural Networks to Streamline the Process of Adaptive Cruise Control

2021 ◽  
Vol 13 (8) ◽  
pp. 4572
Author(s):  
Jiří David ◽  
Pavel Brom ◽  
František Starý ◽  
Josef Bradáč ◽  
Vojtěch Dynybyl
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Adaptive Cruise Control ◽  
Control Unit ◽  
Driving Safety ◽  
Model Parameters ◽  
Cruise Control ◽  
Artificial Neural ◽  
Dynamic Obstacle ◽  
Braking Process

This article deals with the use of neural networks for estimation of deceleration model parameters for the adaptive cruise control unit. The article describes the basic functionality of adaptive cruise control and creates a mathematical model of braking, which is one of the basic functions of adaptive cruise control. Furthermore, an analysis of the influences acting in the braking process is performed, the most significant of which are used in the design of deceleration prediction for the adaptive cruise control unit using neural networks. Such a connection using artificial neural networks using modern sensors can be another step towards full vehicle autonomy. The advantage of this approach is the original use of neural networks, which refines the determination of the deceleration value of the vehicle in front of a static or dynamic obstacle, while including a number of influences that affect the braking process and thus increase driving safety.

Sign in / Sign up

Export Citation Format

Share Document