Results 211 to 220 of about 3,700 (260)

On Langevin Updating in Multilayer Perceptrons

Neural Computation, 1994
The Langevin updating rule, in which noise is added to the weights during learning, is presented and shown to improve learning on problems with initially ill-conditioned Hessians. This is particularly important for multilayer perceptrons with many hidden layers, that often have ill-conditioned Hessians. In addition, Manhattan updating is shown to have
openaire   +2 more sources

On the decision regions of multilayer perceptrons

Proceedings of the IEEE, 1990
The capabilities of two-layer perceptrons are examined with respect to the geometric properties of the decision regions they are able to form. It is known that two-layer perceptrons can form decision regions which are nonconvex and even disconnected, though the extent of their capabilities in comparison to three-layer structures is not well understood.
Gavin J. Gibson, Colin F. N. Cowan
openaire   +1 more source

Multilayer perceptrons and data analysis

IEEE 1988 International Conference on Neural Networks, 1988
Results are presented which permit comparison of classification tasks of multilayer perceptrons with discriminant analysis. The results are illustrated with simulations of both approaches that demonstrate that multilayer perceptrons with nonlinear elements outperform discriminant analysis. >
Patrick Gallinari, Sylvie Thiria, Françoise Fogelman   +2 more
openaire   +1 more source

Multilayer perceptron for nonlinear programming

Computers & Operations Research, 2002
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Jaques Reifman, Earl E. Feldman
openaire   +2 more sources

Dynamic sizing of multilayer perceptrons

Biological Cybernetics, 1994
This article proposes a stochastic method for determining the number of hidden nodes of a multilayer perceptron trained by a backpropagation algorithm. During the learning process, an auxiliary markovian algorithm controls the sizing of the hidden layers.
Bruno Apolloni, G. Ronchini
openaire   +1 more source

MMLD Inference of Multilayer Perceptrons

2013
A multilayer perceptron comprising a single hidden layer of neurons with sigmoidal transfer functions can approximate any computable function to arbitrary accuracy. The size of the hidden layer dictates the approximation capability of the multilayer perceptron and automatically determining a suitable network size for a given data set is an interesting ...
Enes Makalic, Lloyd Allison
openaire   +1 more source

An Enhanced Fuzzy Multilayer Perceptron

2004
Error back-propagation algorithm of the multilayer perceptron may result in local-minima because of the insufficient nodes in the hidden layer, inadequate momentum set-up, and initial weights. In this paper, we proposed the fuzzy multilayer perceptron which is composed of the ART1 and the fuzzy neural network.
Kwang-Baek Kim, Choong Shik Park
openaire   +1 more source

Exponential-weight multilayer perceptron

2017 International Joint Conference on Neural Networks (IJCNN), 2017
Analog integrated circuits may increase the neuromorphic network performance dramatically, leaving far behind their digital and biological counterparts, while approaching the energy efficiency of the brain. The key component of the most advanced analog circuit implementations is a nanodevice with adjustable conductance — essentially an analog ...
Farnood Merrikh-Bayat, Xinjie Guo, Dmitri B. Strukov   +2 more
openaire   +1 more source

An Approach to Encode Multilayer Perceptrons

2002
Genetic connectionism is based on the integration of evolution and neural network learning within one system. An overview of the Multilayer Perceptron encoding schemes is presented. A new approach is shown and tested on various case studies. The proposed genetic search not only optimizes the network topology but shortens the training time.
Jerzy Korczak 0001, Emmanuel Blindauer
openaire   +1 more source

Interactive initialization of the multilayer perceptron

Pattern Recognition Letters, 2000
Abstract A new multilayer preceptor initialization method is proposed and compared experimentally with a traditional random initialization method. An operator maps training-set vectors into a two-variate space, inspects bi-variate training-set vectors and controls the complexity of the decision boundary.
openaire   +1 more source