Commissariat a L'energie Atomique

Xantima LLC

Laurent Herault

Christophe Boulanger

Dominique Derou-Madeline

Dominique Derou

The invention concerns a management process for a network of routers based on the technique of training by reinforcement in which priority is given to objects already present in the network over those which wish to enter.

Adaptive routing process by deflection with training by reinforcement

Direct sequence spread spectrum transmission process that generates and optimizes sequences used by respective users of a communications system. A set of random sequences is produced and the sequences are optimized by a combinatorial operation in order to minimize residual noise. The random sequences belong to an M.sup.th set of roots unity, where respective of the N random sequences have given length L.

Direct sequence spread spectrum transmission process, with generation

Method and apparatus for selecting an optimized subset of trajectories from an available class of potential trajectories in a velocimetry application. In an exemplary method, a neural network is constructed wherein each neuron in the network represents a trajectory in the overall class. A binary output of each neuron indicates whether the object represented by the neuron is to be selected. In the exemplary method, the neural network is in an initially converged state. The network is then alternately excited and constrained so that it settles to additional converged states. During excitation, correction factors including a parameter-optimizing term are applied to neuron input potentials. During constraint, the parameter-optimizing terms are interrupted. Each time the network converges, the outputs of the neurons in the network are decoded to establish a subset of trajectories to be selected, and a value for an optimization parameter associated with the established subset is computed. The excitation and constraint phases are repeated in an attempt to establish subsets of trajectories having superior optimization parameter values. Once the excitation and constraint phases have been repeated a suitable number of times, the trajectories identified in a subset of objects having a superior optimization parameter value are selected. In exemplary embodiments, neurons are updated in a novel block-sequential fashion.

Method and apparatus for using a neural network to extract an optimal

Method and apparatus for selecting an optimal number of trajectories from an available class of potential trajectories in a velocimetry application. In an exemplary method, a neural network is constructed wherein each neuron in the network represents a trajectory in the overall class. A binary output of each neuron indicates whether the trajectory represented by the neuron is to be selected. In the exemplary method, the neural network is initialized with a starting solution wherein the network is in an initially converged state. The network is then alternately excited and constrained so that it settles to additional converged states. During excitation, correction factors including a set-size maximizing term are applied to neuron input potentials. During constraint, the set-size maximizing terms are interrupted. Each time the network converges, the outputs of the neurons in the network are decoded to obtain a subset of trajectories which are to be selected. The excitation and constraint phases are then repeated in an attempt to obtain larger and larger subsets of trajectories to be selected. Once the excitation and constraint phases have been repeated a suitable number of times, the trajectories identified in the largest obtained subset of trajectories are selected.

The invention relates to a process for obtaining trajectories of moving objects, by optimizing at least one criterion from the physics of the phenomenon observed and comprising the following stages: a stage of recording signals (10), a stage (11) of extracting given parts of the signals, a stage (12) of subdividing the group of parts of the signals previously extracted into classes, each class representing a potential trajectory, a stage (13, 14) of selecting a subset of classes satisfying constraints linked with the observed network type, a stage (15) of selecting from among the classes representing the potential trajectories those satisfying the constraints, so as to obtain 'real' trajectories of the objects. The invention also relates to a device for performing this process.

Growing community of inventors

Claix, France

Laurent Herault