Resources Contact Us Home
Browse by: INVENTOR PATENT HOLDER PATENT NUMBER DATE
 
 
Inventor:
Minot; Joel
Address:
Charenton, FR
No. of patents:
6
Patents:












Patent Number Title Of Patent Date Issued
5802507 Method for constructing a neural device for classification of objects September 1, 1998
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
5717687 Data communication system with adaptive routing, and switching node intended to be used in such February 10, 1998
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 the
5649067 Neural device and method of constructing the device July 15, 1997
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
5568591 Method and device using a neural network for classifying data October 22, 1996
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 weight
5481604 Telecommunication network and searching arrangement for finding the path of least cost January 2, 1996
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
5455892 Method for training a neural network for classifying an unknown signal with respect to known sig October 3, 1995
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










 
 
  Recently Added Patents
Auto-aligning spectroscopy system
Method and apparatus to select a profile of a digital communication line
Nanofibers containing latent reactive groups
Dispensing of restricted goods
Digital photographing apparatus and control method for evaluating validity of an auto-focus operation
High voltage circuit for electrical stimulation
Nano-pigment inkjet ink composition that has a low odor and is environmentally-friendly
  Randomly Featured Patents
Detection of noise in a frequency demodulated FM audio broadcast signal
Wideband mud pump noise cancelation method for wellbore telemetry
Touch panel
Passive thermal image glass breakage detector
Radiation collimator for infrared heating and/or cooling of a moving glass sheet
Polyimides from bicyclo[4.2.0]octane-7,8-dimethyl-3,4,7,8-tetracarboxylic acid dianhydride (I) and bicyclo [4.2.0]octane-2,5 diphenyl-7,8-dimethyl-3,4,7,8-tetracarboxylic dianhydride
Ink jet ink compositions and printing processes
Robust magnetizable elastomeric thermoplastic blends
On-site manufacture of ultra-high-purity hydrofluoric acid for semiconductor processing
Carnation named Lontakia