Neuristor-based reservoir computing devices
US-2015379395-A1 · Dec 31, 2015 · US
US10867237B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10867237-B2 |
| Application number | US-201515307269-A |
| Country | US |
| Kind code | B2 |
| Filing date | Apr 24, 2015 |
| Priority date | Apr 28, 2014 |
| Publication date | Dec 15, 2020 |
| Grant date | Dec 15, 2020 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An artificial neuron includes a single-component electric dipole including a single material which belongs to the class of Mott insulators and is connected to first and second electric electrodes.
Opening claim text (preview).
The invention claimed is: 1. An artificial neuron implementing functions of integration, leakage and firing, wherein the artificial neuron consists of: a single-component electrical dipole comprising a material belonging to the family of Mott insulators connected to first and second electrical electrodes, the artificial neuron being a Leaky Integrate-and-Fire (LIF) reference model artificial neuron consisting of the single-component electrical dipole. 2. The artificial neuron according to claim 1 , wherein said Mott insulator material comprises: a compound of formula AM 4 Q 8 , with A comprising at least one of the following elements: Ga, Ge, Zn; M comprising at least one of the following elements: V, Nb, Ta, Mo: and Q comprising at least one of the following elements: S, Se; or an inorganic compound of formula (V 1-x M x ) 2 O 3 , with 0≤x≤1, M comprising at least one of the following elements: Ti, Cr, Fe, Al, or Ga; or an inorganic compound of NiS 2-x Se x , with 0≤x≤1; or a compound of formula VO 2 ; or an organic Mott insulator compound. 3. The artificial neuron according to claim 1 , wherein the first and second electrical electrodes are each constituted by an electrically conductive material comprising: one of the following elements: platinum (Pt), gold (Au), molybdenum (Mo), graphite (C), aluminum (Al), copper (Cu), doped silicon (Si); or one of the following alloys: brass (Cu—Zn), steel (Fe—C), bronze (Cu—Sn); or one of the following transition metal compounds: TiN, TaN, RuO 2 , SrRuO 3 , CuS 2 . 4. The artificial neuron according to claim 1 , wherein said Mott insulator material takes the form of: a thin layer; or a block of crystal; or a nanotube; or a nanowire. 5. A network of neurons comprising a plurality of artificial neurons, wherein at least one artificial neuron is according to claim 1 . 6. A neuromorphic electronic circuit comprising a plurality of artificial neurons, wherein at least one artificial neuron is according to claim 1 . 7. A method for manufacturing an artificial neuron implementing the functions of integration, leakage and firing, wherein the method comprises the following acts: obtaining a material belonging to the family of Mott insulators; obtaining a Leaky Integrate-and-Fire (LIF) reference model artificial neuron consisting of a single-component electrical dipole by deposition of a layer of conductive material: at a first extremity of said Mott insulator material to form a first electrical electrode, and at a second extremity of said Mott insulator material to form a second electrical electrode. 8. The method for manufacturing according to claim 7 , wherein said act of obtaining a material is performed by cutting out a block of Mott insulator crystal, and wherein said act of depositing a layer of conductive material is performed as a function of said cut-out block of crystal. 9. The method for manufacturing according to claim 7 , wherein said act of obtaining a material is performed by depositing, on a substrate wafer, a thin layer of a Mott insulator material, and wherein said act of depositing a layer of conductive material is performed as a function of said deposited thin layer. 10. The method for manufacturing according to claim 7 , wherein said act of obtaining a material is performed by depositing, on a substrate wafer, a nanotube based on a Mott insulator material, and wherein said act of depositing a layer of conductive material is performed as a function of said deposited nanotube. 11. The method for manufacturing according to claim 7 , wherein said act of obtaining a material is performed by depositing, on a substrate wafer, a nanowire based on a Mott insulator material, and wherein said act of depositing a layer of conductive material is performed as a function of said deposited nanowire.
Analogue means · CPC title
Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs · CPC title
using electronic means · CPC title
using resistive RAM [RRAM] elements · CPC title
using elements simulating biological cells, e.g. neuron · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.