Bayesian neural networks and Gaussian processes in identification of concrete properties
Journal Title: Computer Assisted Methods in Engineering and Science - Year 2011, Vol 18, Issue 4
Abstract
This paper gives a concise overview of concrete properties prediction using advanced nonlinear regression approach and Bayesian inference. Feed-forward layered neural network (FLNN) with Markov chain Monte Carlo stochastic sampling and Gaussian process (GP) with maximum likelihood hyperparameters estimation are introduced and compared. An empirical assessment of these two models using two benchmark problems are presented. Results on these benchmark datasets show that Bayesian neural networks and Gaussian processes have rather similar prediction accuracy and are superior in comparison to linear regression model.
Authors and Affiliations
Marek Słoński
Keywords
Related Articles
- EP ID EP74037
- DOI -
- Views 169
- Downloads 0
Method of fundamental solutions and random numbers for the torsion of bars with multiply connected cross sections
The torsion of bars with multiply connected cross section by means of the method of fundamental solutions (MFS) is considered. Random numbers were used to determine the minimal errors for MFS. Five cases of cross section...
Delamination identification using machine learning methods and haar wavelets
The present paper focuses on the identification of delamination size and location in homogeneous and composite laminates. The modal analysis methods are employed to calculate the data patterns. An aggregated approach com...
Experimentally validated numerical model of coupled flow, thermal and electromagnetic problem in small power electric motor
This paper describes results of the mathematical modelling of the steady-state thermal phenomena taking place in a Fracmo 240 W DC electric motor. The model of the motor was defined in the ANSYS Fluent software to predic...
Soft methods in the prediction and identification analysis of axially compressed R/C columns
Two problems are presented in the paper concerning axial loading of R/C columns: I) prediction of critical loads, II) identification of concrete strength. The problems were analyzed by two methods: A) Gaussian Processes...
Formation of graph models for regular finite element meshes. (Received in the final form September 21, 2009)
Graph theory has many applications in structural mechanics and there are also numerous topological transformations which make the related problems simpler. The skeleton graph and natural associate graph of finite element...