This paper presents an extension of the Self Organizing Map model called Associative SOM that is able to process different types of input data in separated data-paths. The ASOM model can easily deal with situations of incomplete data-patterns and incorporate class labels for supervisory purposes. The ASOM is successfully compared with Multilayer Perceptrons in the incremental classification of ...

Various theoretical results show that learning in conventional feedforward neural networks such as multilayer perceptrons is NP-complete. In this paper we show that learning in min-max modular (M3) neural networks is tractable. The key to coping with NP-complete problems in M3 networks is to decompose a large-scale problem into a number of manageable, independent subproblems and to make the lea...

In this paper, a new classifier, called adaptive high order neural tree (AHNT), is proposed for pattern recognition applications. It is a hierarchical multi-level neural network, in which the nodes are organized into a tree topology. It successively partitions the training set into subsets, assigning each subset to a different child node. Each node can be a first-order or a high order perceptro...

An emergence of intelligent behavior within a simple robotic agent is studied in this paper. Two control mechanisms for an agent are considered — new direction of reinforcement learning called relational reinforcement learning, and a radial basis function neural network trained by evolutionary algorithm. Relational reinforcement learning is a new interdisciplinary approach combining logical pro...

This paper introduces a new algorithm to reduce the time of updating the weights of auto-association multilayer perceptrons network. The basic idea is to modify the singular value decomposition which has been used in the batch algorithm to update the weights whenever a new row is added to the input matrix. The computation analysis and the experiments show that the new algorithm speeds up the im...

Neural and neuro-fuzzy models are powerful nonlinear modelling tools. Different structures, with different properties, are widely used to capture static or dynamical nonlinear mappings. Static (non-recurrent) models share a common structure: a nonlinear stage, followed by a linear mapping. In this paper, the separability of linear and nonlinear parameters is exploited for completely supervised ...

Our group is developing artificial neural networks that may be implemented using hybrid semiconductor/molecular (“CMOL”) circuits. Estimates 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 we...

In this paper we show how neural networks can be used as powerful tools for quantitative extraction of relevant information from high resolution transmission electron microscopy (HRTEM) images. Different data preprocessing and modelling strategies (including Multilayer Perceptrons and Probabilistic Neural Networks) were analyzed. The methodology has been applied to the determination of thicknes...

Speech recognition performance degrades significantly when there is a mismatch between testing and training conditions. Linear transformation-based maximum-likelihood (ML) techniques have been proposed recently to tackle this problem. In this paper, we extend this approach to use nonlinear transformations. These are implemented by multilayer perceptrons (MLPs) which transform the Gaussian means...

High order perceptrons are often used in order to reduce the size of neural networks The complexity of the architecture of a usual multilayer network is then turned into the complexity of the functions performed by each high order unit and in particular by the degree of their polynomials The main result of this paper provides a bound on the degree of the polynomial of a high order perceptron wh...