Results 201 to 210 of about 2,193,097 (217)
, 2003 textabstractThe flexibility of neural networks to handle complex data patterns of economic variables is well known. In this survey we present a brief introduction to a neural network and focus on two aspects of its flexibility . First, a neural network is used to recover the dynamic properties of a nonlinear system, in particular, its stability by ...
Kaashoek, J.F., van Dijk, H.K.
openaire +5 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
A neural network to design neural networks
IEEE Transactions on Circuits and Systems, 1991The design of the Hopfield associative memory is reformulated in terms of a constraint satisfaction problem. An electronic neural net capable of solving this problem in real time is proposed. Circuit solutions correspond to symmetrical zero-diagonal matrices that possess few spurious stable states.
openaire +2 more sources
Neural Computation, 1999
A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN.
Søren Riis, Anders Krogh
openaire +3 more sources
A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN.
Søren Riis, Anders Krogh
openaire +3 more sources
Neural networks for consciousness
Neural Networks, 1997The paper outlines a three-stage neural network model for (i) the emergence of consciousness at its lowest level of phenomenal experience, (ii) the development of actions on the emerged conscious activity so as to generate higher-order consciousness. In the model, the lower first stage involves modules transforming inputs into various codes. It is only
openaire +4 more sources
Statistica Neerlandica, 2000
We study the relation between the asymptotic behaviour of synchronous Boltzmann machines and synchronous Hopfield networks. More specifically, we consider the relation between the pseudo consensus function that is used in analyzing Boltzmann machines and the energy function that is used in the study of Hopfield networks.
Ehl Emile Aarts, ten Hmm Huub Eikelder
openaire +3 more sources
We study the relation between the asymptotic behaviour of synchronous Boltzmann machines and synchronous Hopfield networks. More specifically, we consider the relation between the pseudo consensus function that is used in analyzing Boltzmann machines and the energy function that is used in the study of Hopfield networks.
Ehl Emile Aarts, ten Hmm Huub Eikelder
openaire +3 more sources
A Neural Network for Hyphenation
1992Abstract It is shown that although a neural net trained with backprop learning is able to achieve reasonable generalization performance on a hard linguistic pattern recognition problem (segmentation of spelling strings into syllables in Dutch), it remains inferior in performance to symbolic pattern matching algorithms, and even to a simple table ...
Daelemans, Walter, van den Bosch, Antal
openaire +3 more sources
Introduction to Neural Networks: Biological Neural Network
2023Chapter 1 introduces the functional organization of the biological brain. The first section opens with the description of neurons, fundamental units of the brain. These are structures capable of collecting signals, processing them and delivering them to subsequent units.
openaire +2 more sources
Artificial Neural Networks [PDF]
, 2008 Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods.
openaire +2 more sources