We define a Gamma multi-layer perceptron (MLP) as an MLP with the usual synaptic weights replaced by gamma filters (as proposed by de Vries and Principe (de Vries and Principe, 1992)) and associated gain terms throughout all layers. We derive gradient descent update equations and apply the model to the recognition of speech phonemes. We find that both the inclusion of gamma filters in all layer...

Iterative gradient methods such as Levenberg-Marquardt (LM) are in widespread use for source localization from electroencephalographic (EEG) and magnetoencephalographic (MEG) signals. Unfortunately, LM depends sensitively on the initial guess, necessitating repeated runs. This, combined with LM's high per-step cost, makes its computational burden quite high. To reduce this burden, we trained a ...

We deene a Gamma multi-layer perceptron (MLP) as an MLP with the usual synaptic weights replaced by gamma lters (as proposed by de Vries and Principe (de Vries & Principe 1992)) and associated gain terms throughout all layers. We derive gradient descent update equations and apply the model to the recognition of speech phonemes. We nd that both the inclusion of gamma lters in all layers, and the...

In this paper, an empirical comparison of two multilayer perceptron (MLP)-based techniques for keyword speech recognition (wordspotting) is described. The techniques are the predictive neural model (PNM)-based wordspotting, in which the MLP is applied as a speech pattern predictor to compute a local distance between the acoustic vector and the phone model, and the hybrid HMM/MLP-based wordspott...

In this paper, we propose a way to apply Multi Layer Perceptron (MLP) to Functional Data Analysis. We introduce a computation model for functional input data and we show that this model is a well behaving extension of MLP: we show that the proposed model has the universal approximation property. Moreover, parameter estimation for this model is consistent. As a conclusion, we demonstrate functio...

It is easy for a multi-layered perception (MLP) to form open plane classification borders, and for a radial basis function network (RBFN) to form closed circular or elliptic classification borders. In contrast, it is difficult for a MLP to form closed circular or elliptic classification borders, and for RBFN to form open plane classification borders. Hence, MLP and RBFN have their own advantage...

Nowadays, computer scientists have shown the interest in the study of social insect’s behaviour in neural networks area for solving different combinatorial and statistical problems. Chief among these is the Artificial Bee Colony (ABC) algorithm. This paper investigates the use of ABC algorithm that simulates the intelligent foraging behaviour of a honey bee swarm. Multilayer Perceptron (MLP) tr...

MLP is a LIM-only protein of terminally differentiated striated muscle cells, where it accumulates at actin-based structures involved in cytoarchitecture organization. To assess its role in muscle differentiation, we disrupted the MLP gene in mice. MLP (-/-) mice developed dilated cardiomyopathy with hypertrophy and heart failure after birth. Ultrastructural analysis revealed dramatic disruptio...

This paper presents a new approach for automatic image color correction, based on statistical learning. The method both parameterizes color independently of illumination and corrects color for changes of illumination. The motivation for using a learning approach is to deal with changes of lighting typical of indoor environments such as home and office. The method is based on learning color inva...

This work continues in development of the recently proposed Bottle-Neck features for ASR. A five-layers MLP used in bottleneck feature extraction allows to obtai arbitrary feature size without dimensionality reduction by transforms, independently on the MLP training targets. The MLP topology – number and sizes of layers, suitable training targets, the impact of output feature transforms, the ne...