Journal ArticleDOI
Overtraining, Regularization, and Searching for Minimum in Neural Networks
Jonas Sjöberg,Lennart Ljung +1 more
Reads0
Chats0
TLDR
In this article, a neural network model for dynamical systems has been proposed, which is often characterized by the fact that they use a fairly large amount of parameters and is often unsuitable for dynamic systems.About:
This article is published in IFAC Proceedings Volumes.The article was published on 1992-07-01. It has received 123 citations till now. The article focuses on the topics: Time delay neural network & Feedforward neural network.read more
Citations
More filters
Journal ArticleDOI
Nonlinear black-box modeling in system identification: a unified overview
Jonas Sjöberg,Qinghua Zhang,Lennart Ljung,Albert Benveniste,Bernard Delyon,Pierre-Yves Glorennec,Håkan Hjalmarsson,Anatoli Juditsky +7 more
TL;DR: What are the common features in the different approaches, the choices that have to be made and what considerations are relevant for a successful system-identification application of these techniques are described, from a user's perspective.
Journal ArticleDOI
The effects of adding noise during backpropagation training on a generalization performance
TL;DR: It is shown that input noise and weight noise encourage the neural-network output to be a smooth function of the input or its weights, respectively, and in the weak-noise limit, noise added to the output of the neural networks only changes the objective function by a constant, it cannot improve generalization.
Journal ArticleDOI
The statistical-mechanics of learning a rule
TL;DR: In this article, a summary of the statistical mechanical theory of learning a rule with a neural network, a rapidly advancing area which is closely related to other inverse problems frequently encountered by physicists, is presented.
Journal ArticleDOI
On the interpretation and identification of dynamic Takagi-Sugeno fuzzy models
TL;DR: There exists a close relationship between dynamic Takagi-Sugeno fuzzy models and dynamic linearization when using affine local model structures, which suggests that a solution to the multiobjective identification problem exists, but it is also shown that the affineLocal model structure is a highly sensitive parametrization when applied in transient operating regimes.
Journal ArticleDOI
Original Contribution: Improving model selection by nonconvergent methods
TL;DR: This paper shows the general superiority of the ''extended'' nonconvergent methods compared to classical penalty term methods, simple stopped training, and methods which only vary the number of hidden units.
References
More filters
Journal ArticleDOI
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
Numerical Methods for Unconstrained Optimization and Nonlinear Equations (Classics in Applied Mathematics, 16)
TL;DR: In this paper, Schnabel proposed a modular system of algorithms for unconstrained minimization and nonlinear equations, based on Newton's method for solving one equation in one unknown convergence of sequences of real numbers.
Journal ArticleDOI
Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter
TL;DR: The generalized cross-validation (GCV) method as discussed by the authors is a generalized version of Allen's PRESS, which can be used in subset selection and singular value truncation, and even to choose from among mixtures of these methods.
Journal ArticleDOI
Regularization algorithms for learning that are equivalent to multilayer networks.
Tomaso Poggio,Federico Girosi +1 more
TL;DR: A theory is reported that shows the equivalence between regularization and a class of three-layer networks called regularization networks or hyper basis functions.
Proceedings Article
The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems
TL;DR: In this paper, the generalization performance of nonlinear learning systems, such as multilayer perceptrons and radial basis functions, was analyzed for the second order relationship between the expected test set and training set errors.