Proceedings Article10.1109/IJCNN.2007.4371284
Neural Network Initialization with Prototypes - Function Approximation in Engineering Mechanics Applications
Jin-Song Pei,Eric C. Mai,Joseph P. Wright,Andrew W. Smyth +3 more
- 29 Oct 2007
- pp 2110-2116
15
TL;DR: A prototype-based initialization methodology is proposed to approximate functions that are used to characterize nonlinear stress-strain, moment-curvature, and load-displacement relationships, as well as restoring forces and time histories in engineering mechanics applications.
read more
Abstract: A prototype-based initialization methodology is proposed to approximate functions that are used to characterize nonlinear stress-strain, moment-curvature, and load-displacement relationships, as well as restoring forces and time histories in engineering mechanics applications. Three prototypes are defined by exploiting the capabilities of linear sums of sigmoidal functions. By using the proposed prototypes either individually or combinatorially, successful training can take place for ten specific types of nonlinear functions and far beyond when the required number of hidden nodes and initial values of weights and biases can always be derived before the training starts. Some mathematical insights to this initialization methodology and a few prototypes are offered, while training examples are provided to demonstrate a clear procedure that is used to implement this methodology. With the derived numbers of hidden nodes in each approximation, applying the Nguyen-Widrow algorithm is enabled and the training performance is compared between the existing and the proposed initialization options.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Data fusion approaches for structural health monitoring and system identification: Past, present, and future:
TL;DR: A comprehensive review of the recent data fusion applications in structural health monitoring is presented, and state-of-the-art theoretical concepts and applications of data fusion inStructural health monitoring are presented.
187
Deep Convolutional Neural Network for Structural Dynamic Response Estimation and System Identification
TL;DR: This study presents a deep convolutional neural network (CNN)-based approach to estimate the dynamic response of a linear single-degree-of-freedom (SDOF) system, a nonlinear SDOF system, and an...
184
Design of one-dimensional acoustic metamaterials using machine learning and cell concatenation
TL;DR: This study develops two machine learning (ML)-based approaches for the design of one-dimensional periodic and non-periodic metamaterial systems and demonstrates the robustness of the proposed two approaches through numerical simulations and design examples.
59
Mapping some basic functions and operations to multilayer feedforward neural networks for modeling nonlinear dynamical systems and beyond
TL;DR: This study examines linear sums of sigmoidal functions as a means to construct approximations to various nonlinear functions including reciprocal, absolute value, the product of absolute value and first-order polynomial, exponential, truncated sinc, Mexican hat, and Gaussian functions as well as the four elementary arithmetic operations.
23
Demonstration and validation of constructive initialization method for neural networks to approximate nonlinear functions in engineering mechanics applications
Jin-Song Pei,Sami F. Masri +1 more
TL;DR: This study is focused on determining the number of hidden nodes and the initial values of weights and biases for both multilayer feedforward or tapped delay line neural networks, before training them using the well-established backpropagation approach.
12
References
Multilayer feedforward networks are universal approximators
TL;DR: It is rigorously established that standard multilayer feedforward networks with as few as one hidden layer using arbitrary squashing functions are capable of approximating any Borel measurable function from one finite dimensional space to another to any desired degree of accuracy, provided sufficiently many hidden units are available.
23.1K
Approximation by superpositions of a sigmoidal function
TL;DR: It is demonstrated that finite linear combinations of compositions of a fixed, univariate function and a set of affine functionals can uniformly approximate any continuous function ofn real variables with support in the unit hypercube.
•Book
Neural network design
Martin T. Hagan,Howard B. Demuth,Mark Beale +2 more
- 29 Dec 1995
TL;DR: This book, by the authors of the Neural Network Toolbox for MATLAB, provides a clear and detailed coverage of fundamental neural network architectures and learning rules, as well as methods for training them and their applications to practical problems.
6.8K
Structural control: past, present, and future
George W. Housner,Lawrence A. Bergman,Thomas K. Caughey,Anastasios Chassiakos,R. O. Claus,Sami F. Masri,Robert E. Skelton,T. T. Soong,Billie F. Spencer,J. T. P. Yao +9 more
TL;DR: In this paper, the authors provide a concise point of departure for researchers and practitioners alike wishing to assess the current state of the art in the control and monitoring of civil engineering structures, and provide a link between structural control and other fields of control theory.
2.1K
•Book
Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models
Oliver Nelles
- 06 Nov 2000
TL;DR: This chapter discusses Optimization Techniques, which focuses on the development of Static Models, and Applications, which focus on the application of Dynamic Models.
1.7K