Commissariat &#xc0; L'&#xc9;nergie Atomique Et Aux &#xc9;nergies Alternatives

Michel Paindavoine

Marc Duranton

Jean-Marc Philippe

Mehdi Darouich

Stéphane Chevobbe

Stephane Chevobbe

Hong-Phuc Trinh

Sebastien Courroux

Sébastien Courroux

An implementation of neural networks on silicon for the processing of various signals comprises multidimensional signals such as images. The efficient implementation on silicon of a complete processing chain for the signal via the approach using neural networks is provided. The circuit comprises at least: a series of neuro-blocks grouped together in branches composed of a group of neuro-blocks and a broadcasting bus, the neuro-blocks connected to the broadcasting bus; a routing unit connected to the broadcasting bus of the branches, carrying out the routing and broadcasting of data to and from the branches; a transformation module connected to the routing unit via an internal bus and designed to be connected at the input of the circuit to an external databus, the module carrying out the transformation of input data into serial coded data. The processing operations internal to the circuit are carried out according to a serial communications protocol.

Electronic circuit, in particular capable of implementing a neural network, and neural system

A method implemented by a processor for coding a real signal, for example an image signal, into a quantized signal, comprises the following steps applied to each real sample of the real signal: converting the real sample into a digital representation, selecting, in the fractional part of the number, a predetermined number N of most significant non-zero bits, for each non-zero significant bit i selected, i varying from 1 to N, determining its distance Pwith respect to the neighboring selected non-zero significant bit of higher rank or, for the first non-zero significant bit selected, with respect to the decimal point, deducting from the distance Pthe minimum value of distance between two non-zero bits, coding the modified distance Pon a predetermined number Mof bits.

Method of coding a real signal into a quantized signal

A device for decomposing images into at least three levels by wavelet transform comprises a first unit executing a first level of decomposition and a second unit executing the higher levels of decomposition by performing a sequence of processing tasks. The tasks are ordered in time by using a sequence of rows, a routing unit serving to configure the second unit when the level of decomposition associated with the processing task currently being executed changes relative to the level of decomposition associated with the processing task executed previously. The processing tasks are ordered so that any given row is associated with only one level of decomposition.

Device for image decomposition using a wavelet transform

Growing community of inventors

Plombieres les Dijon, France

Michel Paindavoine