| This paper proposes a new method to reduce training time for neural nets used as function approximators. This method relies on a geometrical control of Multilayer Perceptrons (MLP). A geometrical initializa-tion gives rst better starting points for the learning process. A geometrical parametriza-tion achieves then a more stable convergence. During the learning process, a dynamic geometrical c...

The purpose of this paper is to provide a quick overview of neural networks and to explain how they can be used in control systems. We introduce the multilayer perceptron neural network and describe how it can be used for function approximation. The backpropagation algorithm (including its variations) is the principal procedure for training multilayer perceptrons; it is briefly described here. ...

Different kinds of Multilayer Perceptrons, using a back-propagation learning algonthm, have been used to perform data compression tasks. Depending upon the architecture and the type of problern learned to solve ( classification or auto-association), the networks provide different kinds of dimensionality reduction preserving different properties of the data space. Some experiments show that usmg...

Hybrid semiconductor/molecular (“CMOL”) circuits may be used for hardware implementation of artificial neural network. Our studies show that such networks (“CrossNets”) may eventually exceed the mammal brain in areal density, at much higher speed and acceptable power consumption. In this report, we demonstrate that CrossNets based on simple (two-terminal) molecular devices can work well in at l...

We derive here a new method for the analysis of weight quantization effects in multilayer perceptrons based on the application of interval arithmetic. Differently from previous results, we find worst case bounds on the errors due to weight quantization, that are valid for every distribution of the input or weight values. Given a trained network, our method allows to easily compute the minimum n...

There has been much publicity about the ability of artificial neural networks to learn and generalize. In fact, the most commonly used artificial neural networks, called multilayer perceptrons, are nothing more than nonlinear regression and discriminant models that can be implemented with standard statistical software. This paper explains what neural networks are, translates neural network jarg...

AI 057 Abstract The Supervised Growing Neural Gas algorithm (SGNG) provides an interesting alternative to standard multilayer perceptrons (MLP). A comparison is drawn between the performance of SGNG and MLP in the domain of function mapping. A further eld of interest is classiication power, which has been investigated with real data taken by PS197 at CERN. The characteristics of the two network...

Blind extraction of independent sources from their nonlinear mixtures is generally a very difficult problem. This is because both the nonlinear mapping and the underlying sources are unknown, and must be learned in an unsupervised manner from the data. We use multilayer perceptrons as nonlinear generative models for the data, and apply Bayesian ensemble learning for optimizing the model. In thi...

This paper proposes a new method to reduce training time for neural nets used as function approximators. This method relies on a geometrical control of Multilayer Perceptrons (MLP). A geometrical initialization gives first better starting points for the learning process. A geometrical parametrization achieves then a more stable convergence. During the learning process, a dynamic geometrical con...

This paper discusses the use of artificial neural networks, trained with patterns extracted from trail data, as recommender systems. Feed-forward Multilayer-Perceptrons trained with the Backpropagation Algorithm were used to assign a rating to pairs of domains, based on the number of people that had traversed between them. The artificial neural network constructed in this project was capable of...