Commissariat a L'energie Atomique Et Aux Energies Alternatives

Selina La Barbera

Elisa Vianello

Raluca Tiron

Gabriele Navarro

Jean-François Nodin

Jean-Francois Nodin

Niccolo Castellani

Catherine Carabasse

A method of producing a recurrent neural network computer includes consecutive steps of providing a substrate with a first electrode; structuring the first electrode by etching using a first mask made of block copolymers, such that said electrode has free regions which are randomly spatially distributed; forming a resistive-RAM-type memory layer on the first structured electrode; forming a second electrode on the memory layer; and structuring the second electrode by etching, using a second mask made of block copolymers such that said electrode has free regions which are randomly spatially distributed.

Method of producing a recurrent neural network computer

A method for programming a phase change memory cell placed in an initial crystalline state, the memory cell being called of taking a plurality of resistance values belonging to a range of values called 'programming window', the method including parameterizing a lower limit of the programming window by applying to the memory cell a single gradual writing voltage pulse or a first series of identical gradual writing voltage pulses; progressively adjusting the resistance value of the memory cell by the following operations: a gradual erasing operation during which a series of identical gradual erasing voltage pulses is applied to the memory cell; a gradual writing operation during which a second series of identical gradual writing voltage pulses is applied to the memory cell; the gradual writing and gradual erasing voltage pulses have a width less than 50 ns.

Analog method for programming a phase change memory cell by means of identical electrical pulses

The disclosed process includes the successive stages of providing a substrate comprising a dielectric layer; forming a first layer of block copolymers on a part of the dielectric layer, so that the dielectric layer exhibits free zones with a random spatial distribution; etching the free zones, so as to structure the dielectric layer; removing the first layer of block copolymers; forming a first electrode on the structured dielectric layer; forming a memory layer, of resistive memory type, on the first electrode; forming a second electrode on the memory layer; forming a second layer of block copolymers on a part of the second electrode, so that the second electrode exhibits free zones with a random spatial distribution; etching the free zones, so as to structure the second electrode; and removing the second layer of block copolymers.

Process for the manufacture of a recurrent neural network calculator

Growing community of inventors

Grenoble, France

Selina La Barbera