A feature selection procedure is used to successively remove features one-by-one from a statistical classi®er by an iterative backward search. Each classi®er uses a smaller subset of features than the classi®er in the previous iteration. The classi®ers are subsequently combined into a cascade. Each classi®er in the cascade should classify cases to which a reliable class label can be assigned. O...

Learning and reasoning are both aspects of what is considered to be intelligence. Their studies within AI have been separated historically, learning being the topic of machine learning and neural networks, and reasoning falling under classical (or symbolic) AI. However, learning and reasoning are in many ways interdependent. This paper discusses the nature of some of these interdependencies and...

Interpretation of models induced by artiicial neural networks is often a diicult task. In this paper we focus on a relatively novel neural network architecture and learning algorithm, bp-som, that ooers possibilities to overcome this diiculty. It is shown that networks trained with bp-som show interesting regularities, in that hidden-unit activations become restricted to discrete values, and th...

We give a new (inductive) proof of the classical Frobenius– Young correspondence between irreducible complex representations of the symmetric group and Young diagrams, using the new approach, suggested in [11], [15], to determining this correspondence. We also give linear relations between Kostka numbers that follow from the decomposition of the restrictions of induced representations to the pr...

This paper presents a new architecture of neural networks designed for pattern recognition. The concept of induction graphs coupled with a divide-and-conquer strategy defines a Graph of Neural Network (GNN). It is based on a set of several little neural networks, each one discriminating only two classes. The principles used to perform the decision of classification are : a branch quality index ...

It is still controversial whether cranial placodes and neural crest cells arise from a common precursor at the neural plate border or whether placodes arise from non-neural ectoderm and neural crest from neural ectoderm. Using tissue grafting in embryos of Xenopus laevis, we show here that the competence for induction of neural plate, neural plate border and neural crest markers is confined to ...