Abstract: On the basis of a device without hidden neurons, arbitrary samples are taken from a set of learning samples so as to be presented as objects to be classified. Each time if the response is not correct, a hidden neuron (H.sub.i) is introduced with a connection to the output neuron (O.sub.j) of the class of the sample, whereas if the response is correct, no neuron whatsoever is added. During this introduction phase for hidden neurons, the neurons are subdivided into groups by searching for each of the introduced neurons whether it falls within an existing group, in which case it is incorporated therein; otherwise a new group is created around this neuron. The association with a group is defined as a function of the distance from the "creator" neuron. Application: character recognition systems.

Abstract: An adaptive routing protocol for a data communication system that operates in the connection mode. Therefore, the nodes have a function of detecting their neighboring nodes, which permits establishing sessions with their neighbors without previously knowing them, so as to transmit to them recognition messages which indicate their own identifier. Each node additionally has a double identifier of which one identifier is formed by the serial number of the node, so that the serial number can be detected in the system before any configuration and this, more particularly, by a terminal dedicated to managing the system entrusted with the remote configuration of the nodes.

Abstract: On the basis of a device without hidden neurons, arbitrary samples are taken from a set of learning samples so as to be presented as objects to be classified. Each time if the response is not correct, a hidden neuron (H.sub.i) is introduced with a connection to the output neuron (O.sub.j) of the class of the sample, whereas if the response is correct, no neuron whatsoever is added. During this introduction phase for hidden neurons, the neurons are subdivided into groups by searching for each of the introduced neurons whether it falls within an existing group, in which case it is incorporated therein; otherwise a new group is created around this neuron. The association with a group is defined as a function of the distance from the "creator" neuron. This device could be applied in character recognition systems as one example.

Abstract: Method and device having a neural network for classifying data, and verification device for signatures.The device includes a neural network with an input layer 3, an internal layer 4, and an output layer 5. This network is designed to classify data vectors to classes, the synaptic weights in the network being determined through programming on the basis of specimens whose classes are known. Each class is defined during programming as corresponding to a set of neurons of which each represents a domain which contains a fixed number of specimens. The network includes a number of neurons and synaptic weights which have been determined as a function of the classes thus defined.

Abstract: The arrangement is formed by the presence in each node of the network of a cellular automaton comprising cells (0 to 8) interconnected by lines, so that the entirety of the cells and of the lines represents the nodes and the links respectively of the network while each cell comprises calculating means for calculating the cost of a path, works asynchronously, and communicates with each of its nearest neighbouring cells and only with them. When the arrangement is simulated in a sequential machine, this machine is programmed to choose the order in which the cells are activated on the basis of the minimum number of links to be passed through to connect two nodes, which nodes are determined by having the cellular automaton turn when the states of the links are mutually equal.

Abstract: The device includes a neural network with an input layer 3, an internal layer 4, and an output layer 5. This network is designed to classify data vectors to classes, the synaptic weights in the network being determined through programming on the basis of specimens whose classes are known. Each class is defined during programming as corresponding to a set of neurons of which each represents a domain which contains a fixed number of specimens. The network includes a number of neurons and synaptic weights which have been determined as a function of the classes thus defined.