CN111985633A - Method and circuit for simulating artificial perception neuron - Google Patents
Method and circuit for simulating artificial perception neuron Download PDFInfo
- Publication number
- CN111985633A CN111985633A CN202010657004.2A CN202010657004A CN111985633A CN 111985633 A CN111985633 A CN 111985633A CN 202010657004 A CN202010657004 A CN 202010657004A CN 111985633 A CN111985633 A CN 111985633A
- Authority
- CN
- China
- Prior art keywords
- circuit
- neuron
- incident light
- random access
- electrode layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000002569 neuron Anatomy 0.000 title claims abstract description 83
- 230000008447 perception Effects 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000010355 oscillation Effects 0.000 claims abstract description 33
- 239000003990 capacitor Substances 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 14
- XLOMVQKBTHCTTD-UHFFFAOYSA-N Zinc monoxide Chemical compound [Zn]=O XLOMVQKBTHCTTD-UHFFFAOYSA-N 0.000 claims description 30
- GYHNNYVSQQEPJS-UHFFFAOYSA-N Gallium Chemical compound [Ga] GYHNNYVSQQEPJS-UHFFFAOYSA-N 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 15
- 229910052733 gallium Inorganic materials 0.000 claims description 15
- 229910052738 indium Inorganic materials 0.000 claims description 15
- APFVFJFRJDLVQX-UHFFFAOYSA-N indium atom Chemical compound [In] APFVFJFRJDLVQX-UHFFFAOYSA-N 0.000 claims description 15
- 239000011787 zinc oxide Substances 0.000 claims description 15
- 210000001044 sensory neuron Anatomy 0.000 claims description 7
- 239000000758 substrate Substances 0.000 claims description 7
- 229910003087 TiOx Inorganic materials 0.000 claims description 4
- 230000006870 function Effects 0.000 abstract description 6
- 210000005036 nerve Anatomy 0.000 abstract description 3
- 230000000007 visual effect Effects 0.000 description 7
- 229910052751 metal Inorganic materials 0.000 description 6
- 239000002184 metal Substances 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000016776 visual perception Effects 0.000 description 5
- 238000007599 discharging Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 229910052681 coesite Inorganic materials 0.000 description 2
- 229910052906 cristobalite Inorganic materials 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005566 electron beam evaporation Methods 0.000 description 2
- 230000004438 eyesight Effects 0.000 description 2
- 239000000377 silicon dioxide Substances 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 2
- 229910052682 stishovite Inorganic materials 0.000 description 2
- 229910052905 tridymite Inorganic materials 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001755 magnetron sputter deposition Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 108091008695 photoreceptors Proteins 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
- G06N3/065—Analogue means
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Neurology (AREA)
- Solid State Image Pick-Up Elements (AREA)
Abstract
The invention relates to the technical field of artificial nerve morphology, in particular to a method and a circuit for simulating artificial perception neurons, wherein the circuit comprises: an image sensor and an oscillating neuron circuit; an oscillating neuron circuit comprising: the resistive random access memory comprises a resistive random access memory, a capacitor and a load resistor, wherein the resistive random access memory is connected with the capacitor in parallel, and the load resistor is connected with the resistive random access memory in series; the image sensor is connected with the oscillating neuron circuit in series; when receiving incident light with different wavelengths, the image sensor processes the incident light with different wavelengths and outputs different image signals; the oscillation neuron circuit outputs different oscillation signals based on different image signals so as to realize the process of processing incident light with different wavelengths, construct a perception neuron and simulate the function of the perception neuron.
Description
Technical Field
The invention relates to the technical field of artificial nerve morphology, in particular to a method and a circuit for simulating artificial perception neurons.
Background
Human visual perception is an important component of the central nervous system that confers on organisms the ability to process visual information. The human visual perception system is mainly composed of a perception visual signal and a perception cell (photoreceptor), and a processing unit that converts detected information into an electrical peak.
The human visual perception system is capable of simultaneously detecting and processing light information, which is then passed to the various visual centers of the brain, and this structure forms the basis of the combined sensing, preprocessing and encoding capabilities of the human visual system.
At present, researchers have developed some dynamic vision systems based on image sensors and transistor pixel circuits, but these systems occupy a large volume when being manufactured, and require a large amount of computing resources when the systems work, so that the existing dynamic vision systems limit the functions of fully realizing human visual perception.
Therefore, how to fully realize the function of human visual perception is a technical problem to be solved urgently at present.
Disclosure of Invention
In view of the above, the present invention has been developed to provide a method and circuit for simulating artificial sensory neurons that overcomes or at least partially solves the above-mentioned problems.
In a first aspect, the present invention provides a circuit for simulating an artificial perception neuron, comprising:
an image sensor and an oscillating neuron circuit;
wherein the oscillating neuron circuit comprises: the resistive random access memory comprises a resistive random access memory, a capacitor and a load resistor, wherein the resistive random access memory is connected with the capacitor in parallel, and the load resistor is connected with the resistive random access memory in series;
the image sensor is connected in series with the oscillating neuron circuit;
when the image sensor receives incident light with different wavelengths, the incident light with different wavelengths is processed, and different image signals are output;
the oscillation neuron circuit outputs different oscillation signals based on the different image signals so as to realize a process of processing incident light with different wavelengths.
Further, the image sensor is specifically an amorphous indium gallium zinc oxide sensor.
Further, the amorphous indium gallium zinc oxide sensor comprises:
the substrate, the first lower electrode layer, the amorphous indium gallium zinc oxide layer and the first upper electrode layer are arranged from bottom to top.
Further, the first lower electrode layer is Pt, and the first upper electrode layer is Ta.
Further, the resistive random access memory includes:
the second lower electrode layer, the resistance change layer and the second upper electrode layer are arranged from bottom to top.
Further, the resistance change layer is any one of the following:
NbOxlayer, HfOxLayer and TiOxAnd (3) a layer.
Further, the second lower electrode layer is Ta, and the second upper electrode layer is Pt.
In a second aspect, the present invention provides a system for simulating an artificial perception neuron, comprising:
the circuits simulating the artificial perception neurons are connected in series in sequence.
In a third aspect, the present invention further provides a method for simulating an artificial perception neuron, which is applied to the circuit for simulating an artificial perception neuron, and includes:
receiving incident light of different wavelengths;
processing the incident light with different wavelengths to obtain different image signals;
and converting the different image signals to obtain different oscillation signals so as to realize the process of processing the incident light with different wavelengths.
One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:
the invention provides a circuit for simulating an artificial perception neuron, which comprises: an image sensor and an oscillating neuron circuit; wherein the oscillating neuron circuit comprises: the image sensor comprises a resistive random access memory, a capacitor and a load resistor, wherein the resistive random access memory is connected with the capacitor in parallel, the load resistor is connected with the resistive random access memory in series, and the image sensor is connected with the oscillation neuron circuit in series; when the image sensor receives incident light with different wavelengths, the incident light with different wavelengths is processed, and different image signals are output; the oscillating neuron circuit outputs different oscillating signals based on the different image signals to realize a process of processing incident light with different wavelengths, so as to construct a sensing neuron and simulate the function of the sensing neuron.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic diagram of a circuit for simulating a human perception neuron according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an oscillating neuron circuit according to a first embodiment of the present invention;
FIG. 3 is a schematic diagram of an amorphous InGaZn oxide sensor according to an embodiment of the present invention;
fig. 4 shows a schematic structural diagram of a resistive random access memory according to a first embodiment of the present invention;
FIG. 5 is a flow chart illustrating steps of a method for simulating a human sensory neuron according to a second embodiment of the present invention;
fig. 6 shows a schematic structural diagram of a system for simulating a human perception neuron according to a third embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
An embodiment of the present invention provides a circuit for simulating an artificial neuron, as shown in fig. 1, including:
an image sensor 101 and an oscillation neuron circuit 102;
as shown in fig. 2, the oscillating neuron circuit 102 includes: the resistance change memory comprises a resistance change memory 201, a capacitor 202 and a load resistor 203, wherein the resistance change memory 201 is connected with the capacitor 202 in parallel, and the load resistor 203 is connected with the resistance change memory 201 in series;
the image sensor 101 is connected in series with the oscillation neuron circuit 102;
when receiving incident light with different wavelengths, the image sensor 101 processes the incident light with different wavelengths and outputs different image signals;
the oscillating neuron circuit 102 outputs different oscillating signals based on different image signals to realize a process of processing incident light with different wavelengths.
The image sensor 101 is specifically an amorphous indium gallium zinc oxide (a-IGZO) sensor, which is an ultraviolet sensor.
As shown in fig. 3, the amorphous indium gallium zinc oxide (a-IGZO) sensor includes:
a substrate 301, a first lower electrode layer 302, an amorphous InGaZn oxide layer 303, and a first upper electrode layer 304 from bottom to top.
The manufacturing method of the amorphous indium gallium zinc oxide (a-IGZO) sensor comprises the following steps: selecting a substrate 301, in particular SiO2A substrate, followed by forming a layer on the SiO2Generating Pt metal with a preset thickness on the substrate as a first lower electrode 302 by adopting an electron beam evaporation method; then using magnetron sputtering methodAn amorphous indium gallium zinc oxide (a-IGZO) layer 303 is grown, and finally, Ta metal of a predetermined thickness is grown on the amorphous indium gallium zinc oxide (a-IGZO) layer 303 as a first upper electrode layer 304 by an electron beam evaporation method.
Therefore, the first lower electrode 302 uses Pt metal, and the first upper electrode 304 uses Ta metal.
The amorphous indium gallium zinc oxide (a-IGZO) layer 303 has the advantages of high mobility, good uniformity, low temperature treatment in the preparation process, and low cost.
As shown in fig. 4, the resistive random access memory 201 includes: a second lower electrode layer 401, a resistance change layer 402, and a second upper electrode layer 403 from bottom to top.
The resistance change layer 402 is specifically any one of the following: NbOxLayer, HfOxLayer and TiOxAnd (3) a layer.
The second bottom electrode layer 401 is made of Ta, and the second top electrode layer 402 is made of Pt.
After the image sensor 101 and the oscillating neuron circuit 102 are connected in series, a circuit simulating an artificial sensory neuron is formed.
The image sensor 101 is configured to receive incident light with different wavelengths, specifically sense an image, convert the received incident light with different wavelengths into different transmittable image signals, and the oscillation neuron circuit 102 outputs different oscillation signals based on the different image signals, so as to implement a process of processing the incident light with different wavelengths.
The different oscillating signals are spiked into a spiked neuromorphic computer system for further processing. And further realize the identification process of the image.
In a specific embodiment, the oscillation neuron circuit 102 operates as follows:
when the voltage of the input signal of the oscillation neuron circuit is greater than the threshold voltage, the resistance change memory 201 changes from the high resistance state to the low resistance state, so that the capacitor 202 starts to discharge; when the voltage of the input signal of the oscillation neuron circuit falls below the second threshold voltage, the resistance change memory 201 is changed from the low resistance state to the high resistance state, so that the capacitor 202 starts to be charged.
The oscillating signal output by the oscillating neuron circuit 102 is mainly determined by the charging and discharging time of the capacitor 202 in the oscillating neuron circuit 102 and the oscillating frequency formed by the charging and discharging.
The oscillation frequency is specifically determined by the input signal (image signal) of the oscillation neuron element circuit 102, the threshold voltage and the holding voltage of the oscillation neuron element circuit, and the resistance value of the load resistor 203 and the capacitance of the capacitor 202.
The circuit for simulating the artificial perception neuron can sense and convert light image information with different wavelength codes, and transmits the visual information in a parallel mode similar to a biological visual system, so that the construction of the artificial visual system is promoted, and a road is paved for the development of photoelectric devices, optical driving robots and nerve shape calculation inspired by biology.
One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:
the invention provides a circuit for simulating an artificial perception neuron, which comprises: an image sensor and an oscillating neuron circuit; wherein the oscillating neuron circuit comprises: the image sensor comprises a resistive random access memory, a capacitor and a load resistor, wherein the resistive random access memory is connected with the capacitor in parallel, the load resistor is connected with the resistive random access memory in series, and the image sensor is connected with the oscillation neuron circuit in series; when the image sensor receives incident light with different wavelengths, the incident light with different wavelengths is processed, and different image signals are output; the oscillating neuron circuit outputs different oscillating signals based on the different image signals to realize a process of processing incident light with different wavelengths, so as to construct a sensing neuron and simulate the function of the sensing neuron.
Example two
Based on the same inventive concept, the present invention provides a method for simulating an artificial perception neuron, which is applied to a circuit for simulating an artificial perception neuron described in the first embodiment, as shown in fig. 5, and the method includes:
s501, receiving incident light with different wavelengths;
s502, processing the incident light with different wavelengths to obtain different image signals;
and S503, converting the different image signals to obtain different oscillation signals so as to realize a process of processing the incident light with different wavelengths.
In an alternative embodiment, the image sensor can receive incident light of different wavelengths and convert it into different image signals, which are then fed into the oscillating neuron circuit as input signals for the oscillating neuron circuit.
In an alternative embodiment, the neuron circuit for oscillation includes: the image sensor comprises a resistive random access memory, a capacitor and a load resistor, wherein the resistive random access memory is connected with the capacitor in parallel and is connected with the load resistor in series, and the image sensor is connected with the input end of the oscillation neuron circuit.
When the voltage of the input signal of the oscillation neuron circuit is greater than the threshold voltage, the resistance change memory is changed from a high resistance state to a low resistance state, so that the capacitor starts to discharge; when the voltage of the input signal of the oscillation neuron circuit falls below the second threshold voltage, the resistance change memory is changed from a low resistance state to a high resistance state, so that the capacitor starts to be charged.
The oscillation signal output by the oscillation neuron circuit is mainly determined by the charging and discharging time of a capacitor in the oscillation neuron circuit and the oscillation frequency formed by charging and discharging.
Therefore, the artificial perception neurons are simulated by the method, and the functions of the perception neurons are realized.
EXAMPLE III
Based on the same inventive concept, the invention provides a system for simulating artificial perception neurons, comprising: in the first embodiment, the circuits for simulating the artificial perception neurons are sequentially connected in series.
As shown in fig. 6, the circuit includes two analog artificial perception neurons, wherein the first analog artificial perception neuron includes an image sensor 101 and an oscillation neuron circuit 102 connected in series, and the image sensor 101 and the oscillation neuron circuit 102 are connected by a metal wire. The second circuit for simulating artificial perception neurons comprises an image sensor 101 and an oscillation neuron circuit 102 which are connected in series, and the image sensor 101 and the oscillation neuron circuit 102 are connected through metal wires.
The circuit for simulating the artificial perception neurons can simulate a perception behavior, such as the perception of image information in one form, and if the circuits for simulating the artificial perception neurons are adopted, multiple perception behaviors, such as the perception of image information in multiple forms, can be simulated.
In order to simulate the artificial perception neurons truly, various perception behaviors need to be simulated at the same time, and the system for simulating the artificial perception neurons is further adopted, namely, a plurality of circuits for simulating the artificial perception neurons are connected in series.
In an alternative embodiment, the image sensor 101 is embodied as an amorphous indium gallium zinc oxide sensor.
An amorphous indium gallium zinc oxide sensor comprising:
the substrate, the first lower electrode layer, the amorphous indium gallium zinc oxide layer and the first upper electrode layer are arranged from bottom to top.
The first lower electrode layer is Pt, and the first upper electrode layer is Ta.
In an optional embodiment, the resistive random access memory includes: the second lower electrode layer, the resistance change layer and the second upper electrode layer are arranged from bottom to top.
The resistance change layer is any one of the following:
NbOxlayer, HfOxLayer and TiOxAnd (3) a layer.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A circuit for simulating an artificial perception neuron, comprising:
an image sensor and an oscillating neuron circuit;
wherein the oscillating neuron circuit comprises: the resistive random access memory comprises a resistive random access memory, a capacitor and a load resistor, wherein the resistive random access memory is connected with the capacitor in parallel, and the load resistor is connected with the resistive random access memory in series;
the image sensor is connected in series with the oscillating neuron circuit;
when the image sensor receives incident light with different wavelengths, the incident light with different wavelengths is processed, and different image signals are output;
the oscillation neuron circuit outputs different oscillation signals based on the different image signals so as to realize a process of processing incident light with different wavelengths.
2. The circuit according to claim 1, wherein the image sensor is in particular an amorphous indium gallium zinc oxide sensor.
3. The circuit of claim 2, wherein the amorphous indium gallium zinc oxide sensor comprises:
the substrate, the first lower electrode layer, the amorphous indium gallium zinc oxide layer and the first upper electrode layer are arranged from bottom to top.
4. The circuit of claim 3, wherein the first lower electrode layer is Pt and the first upper electrode layer is Ta.
5. The circuit of claim 1, wherein the resistive random access memory comprises:
the second lower electrode layer, the resistance change layer and the second upper electrode layer are arranged from bottom to top.
6. The circuit of claim 5, wherein the resistive layer is any one of:
NbOxlayer, HfOxLayer and TiOxAnd (3) a layer.
7. The circuit of claim 5, wherein the second lower electrode layer is Ta and the second upper electrode layer is Pt.
8. A system for simulating an artificial perception neuron, comprising:
a plurality of circuits for emulating an artificial sensory neuron according to any one of claims 1-7, said plurality of circuits for emulating an artificial sensory neuron being serially connected in series.
9. A method of emulating an artificial sensory neuron, the method being applied to a circuit for emulating an artificial sensory neuron according to any one of claims 1-7, the method comprising:
receiving incident light of different wavelengths;
processing the incident light with different wavelengths to obtain different image signals;
and converting the different image signals to obtain different oscillation signals so as to realize the process of processing the incident light with different wavelengths.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010657004.2A CN111985633A (en) | 2020-07-09 | 2020-07-09 | Method and circuit for simulating artificial perception neuron |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010657004.2A CN111985633A (en) | 2020-07-09 | 2020-07-09 | Method and circuit for simulating artificial perception neuron |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111985633A true CN111985633A (en) | 2020-11-24 |
Family
ID=73438585
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010657004.2A Pending CN111985633A (en) | 2020-07-09 | 2020-07-09 | Method and circuit for simulating artificial perception neuron |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111985633A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113675223A (en) * | 2021-05-17 | 2021-11-19 | 松山湖材料实验室 | Photoelectric synapse device and application thereof |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110199390A (en) * | 2017-01-26 | 2019-09-03 | Hrl实验室有限责任公司 | Expansible, stackable and BEOL process compatible integrated neuron circuit |
CN110647982A (en) * | 2019-09-26 | 2020-01-03 | 中国科学院微电子研究所 | Artificial sensory nerve circuit and preparation method thereof |
-
2020
- 2020-07-09 CN CN202010657004.2A patent/CN111985633A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110199390A (en) * | 2017-01-26 | 2019-09-03 | Hrl实验室有限责任公司 | Expansible, stackable and BEOL process compatible integrated neuron circuit |
CN110647982A (en) * | 2019-09-26 | 2020-01-03 | 中国科学院微电子研究所 | Artificial sensory nerve circuit and preparation method thereof |
Non-Patent Citations (1)
Title |
---|
鲍晴峰: "基于脉冲藕合神经网络的图像信息处理", 中国优秀硕士学位论文全文数据库信息科技辑, 15 August 2006 (2006-08-15), pages 1 - 45 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113675223A (en) * | 2021-05-17 | 2021-11-19 | 松山湖材料实验室 | Photoelectric synapse device and application thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110998611B (en) | Nerve morphology processing device | |
US9818057B2 (en) | Neural network circuit and learning method thereof | |
US20190122105A1 (en) | Training of artificial neural networks | |
CN102456157B (en) | Neuron chip and neural network | |
US11468300B2 (en) | Circuit structure and driving method thereof, neural network | |
CN110647982B (en) | Artificial sensory nerve circuit and preparation method thereof | |
US20130311414A1 (en) | Learning method of neural network circuit | |
CN103078054A (en) | Unit, device and method for simulating biological neuron and neuronal synapsis | |
CN111121607B (en) | Method for training three-dimensional positioning model and three-dimensional positioning method and device | |
US11043265B2 (en) | Memory devices with volatile and non-volatile behavior | |
CN111985633A (en) | Method and circuit for simulating artificial perception neuron | |
Ye et al. | Self-powered perception system based on triboelectric nanogenerator and artificial neuron for fast-speed multilevel feature recognition | |
CN109165731B (en) | Electronic neural network and parameter setting method thereof | |
CN117669676A (en) | Memristor-based sensing neuron circuit and application | |
KR101805247B1 (en) | Neuromorphic Pattern Classifier of using Metal-Insulator Transition Device and Method of Classifying Pattern | |
Ochs et al. | Anticipation of digital patterns | |
KR102092549B1 (en) | 2 dimensional sensor and touch sensor | |
KR101510991B1 (en) | Neuromorphic Pattern Classifier of using Resistance Changing Memory and Method of Classifying the Pattern | |
CN113532489A (en) | Capacitance type sensing architecture based on mott insulator memristor | |
Liao et al. | A Gate Multiplexing Architecture‐Based Artificial Visual Sensor and Memory System | |
CN113390464A (en) | Resistance-variable sensing framework for coded pulse output | |
CN111933197B (en) | Method and circuit for processing detected signal | |
Lin et al. | Resistive memory-based zero-shot liquid state machine for multimodal event data learning | |
CN112396176A (en) | Hardware neural network batch normalization system | |
Wang et al. | On non-von Neumann flexible neuromorphic vision sensors |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |