I. Abstract It is well-established that a multi-layer perceptron (MLP) with a single hidden layer of N neurons and an activation function bounded by zero at negative infinity and one at infinity can learn N distinct training sets with zero error. Previous work has shown that the input weights and biases for such a MLP can be chosen in an effectively arbitrary manner; however, this work makes th...

In this study, we propose a Multi-Layer Perceptron (MLP) with pulse glial network having dynamic period of inactivity. We connect glias to neurons in a hidden-layer. The glia is excited by the connecting neuron output. Then, the glia generates a pulse. The pulse is propagated to the connecting neuron and the neighboring glia. In the previous method, we fix a period of inactivity. The period of ...

This paper concerns dynamic neural networks for signal processing: architectural issues are considered but the paper focuses on learning algorithms that work on-line. Locally recurrent neural networks, namely MLP with IIR synapses and generalization of Local Feedback MultiLayered Networks (LF MLN), are compared to more traditional neural networks, i.e. static MLP with input and/or output buffer...

Muscle LIM protein (MLP) is a member of the cysteine rich protein family and has so far been regarded as a muscle-specific protein that is mainly involved in myogenesis and the organization of cytoskeletal structure in myocytes, respectively. The current study demonstrates for the first time that MLP expression is not restricted to muscle tissue, but is also found in the rat naive central nervo...

A maternal low-protein diet (MLP) fed during pregnancy leads to hypertension in adult rat offspring. Hypertension is a major risk factor for ischaemic heart disease. This study examined the capacity of hearts from MLP-exposed offspring to recover from myocardial ischaemia-reperfusion (IR) and related this to cardiac expression of β-adrenergic receptors (β-AR) and their associated G proteins. Pr...

This paper presents a new statistical approach for learning automatic color image correction. The goal is to parameterize color independently of illumination and to correct color for changes of illumination. This is useful in many image processing applications, such as color image segmentation or background subtraction. The motivation for using a learning approach is to deal with changes of lig...

This paper presents an original hybrid MLP-SVM method for unconstrained handwritten digits recognition. Specialized Support Vector Machines (SVMs) are introduced to improve significantly the MLP performances in local areas around the separation surfaces between each pair of digit classes, in the input pattern space. This hybrid architecture is based on the idea that the correct digit class almo...

This paper concerns dynamic neural networks for signal processing: architectural issues are considered but the paper focuses on learning algorithms that work on-line. Locally recurrent neural networks, namely MLP with IIR synapses and generalization of Local Feedback MultiLayered Networks (LF MLN), are compared to more traditional neural networks, i.e. static MLP with input and/or output buffer...

A signal su ers from nonlinear, linear, and additive distortion when transmitted through a channel. Linear equalizers are commonly used in receivers to compensate for linear channel distortion. As an alternative, nonlinear equalizers have the potential to compensate for all three sources of channel distortion. Previous authors have shown that nonlinear feedforward equalizers based on either mul...