In this paper, we propose a new way to use Functional MultiLayer Perceptrons (FMLP). In our previous work, we introduced a natural extension of Multi Layer Perceptrons (MLP) to functional inputs based on direct manipulation of input functions. We propose here to rely on a representation of input and weight functions thanks to projection on a truncated base. We show that the proposed model has t...

Perceptrons with graded input-output relations and a limited output precision are studied within the Gardner–Derrida canonical ensemble approach. Soft non-negative error measures are introduced allowing for extended retrieval properties. In particular, the performance of these systems for a linear and quadratic error measure, corresponding to the perceptron respectively the adaline learning alg...

A large fraction of recent work in artificial neural nets uses multilayer perceptrons trained with the back-propagation algorithm described by Rumelhart et. a1. This algorithm converges slowly for large or complex problems such as speech recognition, where thousands of iterations may be needed for convergence even with small data sets. In this paper, we show that training multilayer perceptrons...

We present a phrase recognition system based on perceptrons, and an online learning algorithm to train them together. The recognition strategy applies learning in two layers, first at word level, to filter words and form phrase candidates, second at phrase level, to rank phrases and select the optimal ones. We provide a global feedback rule which reflects the dependencies among perceptrons and ...

In this study we propose a new ensemble model composed of several linear perceptrons. The objective of this study is to build a piecewise-linear classifier that is not only competitive to Multilayer Perceptrons(MLP) in generalization performance but also interpretable in the form of human-comprehensible rules. We present a simple competitive training method that allows the ensemble to effective...

The statistical mechanics of two-layered perceptrons with N input units, K hidden units, and a single output unit that makes a decision based on a majority rule (Committee Machine), is studied. Two architectures are considered. In the nonoverlapping case the hidden units do not share common inputs. In the fully connected case each hidden unit is connected to the entire input layer. In both case...

We consider nonlinear quantile regression involving multilayer perceptrons (MLP). In this paper we investigate the asymptotic behavior of quantile regression in a general framework. First by allowing possibly non-identifiable regression models like MLP's with redundant hidden units, then by relaxing the conditions on the density of the noise. In this paper, we present an universal bound for the...