Publications

1994

• Visualisation tridimensionnelle de la dynamique de la superposition linéaire de 6 états propres de l'atome d'Hydrogène (calcul tridimensionnel)
  
  • Colonna Jean-François
  , 1994. Tridimensional display of the dynamics of a linear superposition of 6 eigenstates of the Hydrogen atom (tridimensional computation) (Visualisation tridimensionnelle de la dynamique de la superposition linéaire de 6 états propres de l'atome d'Hydrogène (calcul tridimensionnel))
• Visualisation tridimensionnelle de la dynamique de la superposition linéaire de 6 états propres de l'atome d'Hydrogène (calcul tridimensionnel)
  
  • Colonna Jean-François
  , 1994. Tridimensional display of the dynamics of a linear superposition of 6 eigenstates of the Hydrogen atom (tridimensional computation) (Visualisation tridimensionnelle de la dynamique de la superposition linéaire de 6 états propres de l'atome d'Hydrogène (calcul tridimensionnel))
• Autostereogramme d'un ensemble de Julia dans le corps des quaternions
  
  • Colonna Jean-François
  , 1994. Autostereogram of a quaternionic Julia set (Autostereogramme d'un ensemble de Julia dans le corps des quaternions)
• Genetic algorithms for optimal plane conflict resolution in air traffic
  
  • Durand Nicolas
  • Alech Nicolas
  • Alliot Jean-Marc
  • Schoenauer Marc
  , 1994, pp.pp xxxx. At the dawn of civil aviation, pilots resolved conflicts themselves because they always flew in good weather conditions with low speed aircrafts. Nowadays, pilots must be helped by an air traffic controller on the ground who has a global view of the current traffic distribution in the airspace and can give indications to the pilots to avoid collisions. Solutions to conflicts are empirical, controllers are trained to react to certain types of conflicts and are limited by a workload. It is clear that if the ATC is overloaded, the sky is not. Conflict resolution is a trajectory optimization problem under constraints the complexity of which is so important that it has not been solved yet. Many attempts have been made to solve this problem with classical methods, such as gradient methods, reactive technics, expert systems, but most of them failed. In this paper, we show how genetic algorithms can be used to solve en-route aircrafts conflict automatically to increase Air Traffic Control capacity in high density areas. Our main purpose is to find out the global optimum and not only a suitable solution, in a real time situation, with conflict free trajectories that respect both plane and pilot performances.
• Genetic lander: An experiment in accurate neuro-genetic control
  
  • Ronald Edmund
  • Schoenauer Marc
  , 1994, 866, pp.452 - 461. The control problem of soft-landing a toy lunar module sim-ulation is investigated in the context of neural nets. While traditional supervised back-propagation training is inappropriate for lack of train-ing exemplars, genetic algorithms allow a controller to be evolved with-out diiculty: Evolution is a form of unsupervised learning. A novelty introduced in this paper is the presentation of additional renormalized inputs to the net; experiments indicate that the presence of such inputs allows precision of control to be attained faster, when learning time is measured by the number of generations for which the GA must run to attain a certain mean performance. (10.1007/3-540-58484-6_288)
  DOI : 10.1007/3-540-58484-6_288
• Autostereogramme d'un ensemble de Julia dans le corps des quaternions avec des phenomenes fractals
  
  • Colonna Jean-François
  , 1994. Autostereogram of a quaternionic Julia set and fractal phenomenon (Autostereogramme d'un ensemble de Julia dans le corps des quaternions avec des phenomenes fractals)
• Genetic Extensions of Neural Net Learning: Transfer Functions and Renormalisation Coefficients
  
  • Schoenauer Marc
  • Ronald Edmund
  , 1994. This paper deals with technical issues relevant to artificial neural net (ANN) training by genetic algorithms. Neural nets have applications ranging from perception to control; in the context of control, achieving great precision is more critical than in pattern recognition or classification tasks. In previous work, the authors have found that when employing genetic search to train a net, both precision and training speed can be greatly enhanced by an input renormalisation technique. In this paper we investigate the automatic tuning of such renormalisation coefficients, as well as the tuning of the slopes of the transfer functions of the individual neurons in the net. Waiting time analysis is presented as an alternative to the classical "mean perfomance" interpretation of GA experiments. It is felt that it provides a more realistic evaluation of the real-world usefulness of a GA.
• Controlling Crossover through Inductive Learning
  
  • Sebag Michèle
  • Schoenauer Marc
  , 1994, pp.209-218. Crossover may achieve the fast combination of performant building blocks ; but as a counterpart, crossover may as well break a newly discovered building block. We propose to use inductive learning to control such disruptive effects of crossover. The idea is to periodically gather some examples of crossovers, labelled as "good" or "bad" crossovers according to their effects on the current population. From these examples, inductive learning builds rules characterizing the crossover quality. This ruleset then enables to control further evolution : crossovers classified "bad" according to the ruleset are refused. Some experimentations on the Royal Road problem are discussed.
• Genetic algorithms for air traffic assignment
  
  • Delahaye Daniel
  • Alliot Jean-Marc
  • Schoenauer Marc
  • Farges Jean-Loup
  , 1994, pp.pp 372-376. In this paper, we show how genetic algorithms can be used to compute automatically a traffic assignment of aircraft on the air network to increase Air Traffic Control capacity in high density areas.
• Autostereogramme en vraies couleurs d'un ensemble de Julia dans le corps des quaternions
  
  • Colonna Jean-François
  , 1994. True colors autostereogram of a quaternionic Julia set (Autostereogramme en vraies couleurs d'un ensemble de Julia dans le corps des quaternions)
• Autostereogramme d'un ensemble de Julia dans le corps des quaternions
  
  • Colonna Jean-François
  , 1994. Autostereogram of a quaternionic Julia set (Autostereogramme d'un ensemble de Julia dans le corps des quaternions)
• Feature induction by backpropagation
  
  • Ronald Edmund
  • Schoenauer Marc
  • Sebag Michèle
  , 1994, pp.531-534 vol.1. A method for investigating the internal knowledge representation constructed by neural net learning is described: it is shown how from a given weight matrix defining a feedforward artificial neural net, we can induce characteristic patterns of each of the classes of inputs classified by that net. These characteristic patterns, called prototypes, are found by a gradient descent search of the space of inputs. After an exposition of the theory, results are given for the well known LED recognition problem where a network simulates recognition of decimal digits displayed on a seven-segment LED display. Contrary to theoretical intuition, the experimental results indicate that the computed prototypes retain only some of the features of the original input patterns. Thus it appears that the indicated method extracts those features deemed significant by the net. (10.1109/ICNN.1994.374220)
  DOI : 10.1109/ICNN.1994.374220
• Neuro-Genetic Truck Backer-Upper Controller
  
  • Schoenauer Marc
  • Ronald Edmund
  , 1994. The precise docking of a truck at a loading dock has been proposed in Nguyen & Widrow 90] as a benchmark problem for non-linear control by neural-nets. The main difficulty is that back-propagation is not a priori suitable as a learning paradigm, because no set of training vectors is available: It is non-trivial to find solution trajectories that dock the truck from anywhere in the loading yard. In this paper we show how a genetic algorithm can evolve the weights of a feed-forward 3-layer neural net that solves the control problem for a given starting state, achieving a short trajectory from starting point to goal. The fitness of a net in the population is a function of both the nearest position from the goal and the distance traveled. The influence of input data renormalisation on trajectory precision is also discussed.
• Interaction électron-neutrino
  
  • Colonna Jean-François
  , 1994. Electron-neutrino scattering (Interaction électron-neutrino)
• Interaction électron-positron
  
  • Colonna Jean-François
  , 1994. Electron-positron scattering (Interaction électron-positron)
• Genetic algorithms for partitioning air space
  
  • Delahaye Daniel
  • Alliot Jean-Marc
  • Schoenauer Marc
  • Farges Jean-Loup
  , 1994, pp.pp 291-297. In this paper, we show how genetic algorithms can be used to compute automatically a balanced sectoring of air-space to increase air traffic control capacity in high density areas. (10.1109/CAIA.1994.323662)
  DOI : 10.1109/CAIA.1994.323662
• Un coquillage (surface de Jeener 1) en mouvement
  
  • Colonna Jean-François
  , 1994. A shell (Jeener surface 1) in motion (Un coquillage (surface de Jeener 1) en mouvement)
• Vue artistique d'un ensemble de Julia dans le corps des quaternions
  
  • Colonna Jean-François
  , 1994. Artistic view of a quaternionic Julia set (Vue artistique d'un ensemble de Julia dans le corps des quaternions)
• L'attracteur de Lorenz
  
  • Colonna Jean-François
  , 1994. The Lorenz attractor (L'attracteur de Lorenz)
• Reconstruction d'une structure bidimensionnelle -la carte de France
  
  • Colonna Jean-François
  , 1994. Reconstruction of a 2D structure -the map of France- (Reconstruction d'une structure bidimensionnelle -la carte de France-)
• Solving the inverse fractal problem from wavelet analysis
  
  • Arneodo Alain
  • Bacry Emmanuel
  • Muzy Jean-François
  EPL - Europhysics Letters, European Physical Society / EDP Sciences / Società Italiana di Fisica / IOP Publishing, 1994, 25 (7), pp.479-484. We report on a wavelet-based technique for solving the inverse fractal problem. We show that one can uncover a dynamical system which leaves invariant a given fractal object from the space scale arrangement of its wavelet transform modulus maxima. Our purpose is illustrated on Bernoulli invariant measures of linear as well as non-linear "cookie-cutters". Application to period-doubling dynamical systems at the onset of chaos is reported. (10.1209/0295-5075/25/7/001)
  DOI : 10.1209/0295-5075/25/7/001
• THE MULTIFRACTAL FORMALISM REVISITED WITH WAVELETS
  
  • Muzy J. F.
  • Bacry Emmanuel
  • Arneodo A.
  International journal of bifurcation and chaos in applied sciences and engineering, World Scientific Publishing, 1994, 4 (2), pp.245-302. no abstract (10.1142/s0218127494000204)
  DOI : 10.1142/s0218127494000204