In many applications, high dimensional input data can be considered as sampled functions. We show in this paper how to use this prior knowledge to implement functional preprocessings that allow to consistently reduce the dimension of the data even when they have missing values. Preprocessed functions are then handled by a numerical MLP which approximates the theoretical functional MLP. A succes...

This letter proposes a new type of neurons called multithreshold quadratic sigmoidal neurons to improve the classification capability of multilayer neural networks. In cooperation with single-threshold quadratic sigmoidal neurons, the multithreshold quadratic sigmoidal neurons can be used to improve the classification capability of multilayer neural networks by a factor of four compared to comm...

This paper presents the use of a genetic programming (GP) system called STROGANOFF and a multilayer perceptron for thalassemic patient classification. The interested problem covers the test samples from normal subjects and that from different types of thalassemic patient and thalassemic trait. The features, which are the characteristics of red blood cell, Thalassemic Patient Classification Usin...

|This paper proposes new methods of generating input locations actively in gathering training data, aiming at solving problems special to multilayer perceptrons. One of the problems is that the optimum input locations which are calculated deterministically sometimes result in badly-distributed data and cause local minima in back-propagation training. Two probabilistic active learning methods, w...

This section introduces multilayer perceptrons, which are the most commonly used type of neural network. The popular backpropagation training algorithm is studied in detail. The momentum and adaptive step size techniques, which are used for accelerated training, are discussed. Other acceleration techniques are briefly referenced. Several implementation issues are then examined. The issue of gen...

We propose an active learning method with hidden-unit reduction, which is devised specially for multilayer perceptrons (MLP). First, we review our active learning method, and point out that many Fisher-information-based methods applied to MLP have a critical problem: the information matrix may be singular. To solve this problem, we derive the singularity condition of an information matrix, and ...