CN113177637B - Neuron simulation device and control method thereof - Google Patents
Neuron simulation device and control method thereof Download PDFInfo
- Publication number
- CN113177637B CN113177637B CN202110377708.9A CN202110377708A CN113177637B CN 113177637 B CN113177637 B CN 113177637B CN 202110377708 A CN202110377708 A CN 202110377708A CN 113177637 B CN113177637 B CN 113177637B
- Authority
- CN
- China
- Prior art keywords
- module
- neuron
- field effect
- pulse signal
- effect transistor
- 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.)
- Active
Links
- 210000002569 neuron Anatomy 0.000 title claims abstract description 105
- 238000004088 simulation Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 14
- 230000005669 field effect Effects 0.000 claims abstract description 48
- 230000010287 polarization Effects 0.000 claims abstract description 18
- 238000009825 accumulation Methods 0.000 claims abstract description 15
- 230000015556 catabolic process Effects 0.000 claims abstract description 12
- 238000006731 degradation reaction Methods 0.000 claims abstract description 12
- 239000003990 capacitor Substances 0.000 claims description 15
- 230000002964 excitative effect Effects 0.000 claims description 5
- 238000010304 firing Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 claims 1
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 210000002364 input neuron Anatomy 0.000 description 3
- 230000000638 stimulation Effects 0.000 description 3
- MCMNRKCIXSYSNV-UHFFFAOYSA-N Zirconium dioxide Chemical compound O=[Zr]=O MCMNRKCIXSYSNV-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- CJNBYAVZURUTKZ-UHFFFAOYSA-N hafnium(IV) oxide Inorganic materials O=[Hf]=O CJNBYAVZURUTKZ-UHFFFAOYSA-N 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- PNEYBMLMFCGWSK-UHFFFAOYSA-N aluminium oxide Inorganic materials [O-2].[O-2].[O-2].[Al+3].[Al+3] PNEYBMLMFCGWSK-UHFFFAOYSA-N 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003592 biomimetic effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 229910052593 corundum Inorganic materials 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003989 dielectric material Substances 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
- 229910001845 yogo sapphire Inorganic materials 0.000 description 1
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
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L29/00—Semiconductor devices specially adapted for rectifying, amplifying, oscillating or switching and having potential barriers; Capacitors or resistors having potential barriers, e.g. a PN-junction depletion layer or carrier concentration layer; Details of semiconductor bodies or of electrodes thereof ; Multistep manufacturing processes therefor
- H01L29/66—Types of semiconductor device ; Multistep manufacturing processes therefor
- H01L29/68—Types of semiconductor device ; Multistep manufacturing processes therefor controllable by only the electric current supplied, or only the electric potential applied, to an electrode which does not carry the current to be rectified, amplified or switched
- H01L29/76—Unipolar devices, e.g. field effect transistors
- H01L29/772—Field effect transistors
- H01L29/78—Field effect transistors with field effect produced by an insulated gate
- H01L29/78391—Field effect transistors with field effect produced by an insulated gate the gate comprising a layer which is used for its ferroelectric properties
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Neurology (AREA)
- Power Engineering (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Ceramic Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Thin Film Transistor (AREA)
- Tests Of Electronic Circuits (AREA)
Abstract
The invention discloses a neuron simulation device and a control method thereof, wherein the device comprises: a first module, a second module, and a third module; the second module comprises an amorphous ferroelectric field effect transistor and is used for enabling the neuron simulation device to be restored to an initialized state under the action of polarization degradation characteristics of the amorphous ferroelectric field effect transistor; the first module, the second module and the third module are respectively used for simulating the accumulation characteristic, the leakage characteristic and the emission characteristic of the neuron; the first module and the third module are both connected with the second module, and the second module is also respectively connected with a first power supply and a pulse signal generating device outside the neuron simulation device. The embodiment of the invention can improve the operation simplicity of neuron simulation and improve the simulation effect of neurons.
Description
Technical Field
The invention relates to the field of impulse neural networks, in particular to a neuron simulation device and a control method thereof.
Background
In the conventional Von Neumann architecture, the processing unit is separated from the memory unit, resulting in considerable delay and energy overhead. With the rapid development of information technology, the conventional Von Neumann architecture cannot cope with the requirements of higher computational power and lower power consumption, so that development of a new computing architecture is needed. Inspired by the calculation mode of the human brain, researchers have proposed the calculation architecture of neural networks. The neural network has parallel and efficient computing power, and can overcome the bottleneck of a memory wall of the traditional Von Neumann architecture.
A pulsed neural network, which mimics neurons more nearly physically, has its membrane potential activated until it reaches a certain value. When one neuron is activated, a signal is generated to transmit to the other neuron, thereby raising or lowering its membrane potential. Its basic function can be abstracted into an accumulation-leakage-emission model (LIF). When the neuron accumulates to a certain potential, a transmitting function is realized. Leakage is the introduction of a constant bleed path to the accumulation of neurons. The LIF model is the most widely used biomimetic impulse neuron model in neuromorphic computation.
In the hardware implementation of the impulse neural network, the traditional MOSFET implementation method has the defects of high hardware cost, high circuit energy consumption and the like, and is unfavorable for high-density integration. The realization method of FeFET utilizes spontaneous polarization modulation channel conductivity of ferroelectric material, can greatly reduce hardware cost and improve integration density. However, fefets cannot simulate leakage characteristics by their own characteristics, and after one LIF cycle is completed, a reset voltage needs to be applied to adjust the polarization state of the ferroelectric thin film to an initial state.
Disclosure of Invention
The embodiment of the invention provides a neuron simulation device and a control method thereof, which improve the operation simplicity of neuron simulation and improve the simulation effect of neurons.
A first aspect of embodiments of the present application provides a neuron simulation device, including: the first module, the second module and the third module are respectively used for simulating the accumulation characteristic, the leakage characteristic and the emission characteristic of the neuron;
the second module comprises an amorphous ferroelectric field effect transistor, wherein the amorphous ferroelectric field effect transistor has polarization degradation characteristics and is used for enabling the neuron simulation device to recover to an initialized state;
the first module and the third module are both connected with the second module, and the second module is also respectively connected with a first power supply and a pulse signal generating device outside the neuron simulation device.
In a possible implementation manner of the first aspect, the first module and the third module are both connected with the second module, and the second module is further connected with a first power supply and a pulse signal generating device outside the neuron analog device respectively, specifically:
the drain electrode of the amorphous ferroelectric field effect transistor is respectively connected with the first module and the third module; the source electrode of the amorphous ferroelectric field effect transistor is connected with a first power supply outside the neuron simulation device, and the grid electrode of the amorphous ferroelectric field effect transistor is connected with a pulse signal generating device outside the neuron simulation device.
In a possible implementation manner of the first aspect, the drains of the amorphous ferroelectric field effect transistors are connected to the first module and the third module respectively, specifically:
the first module comprises a capacitor, and the third module comprises a resistor and a switch;
one end of the capacitor is connected with the drain electrode of the amorphous ferroelectric field effect transistor, and the other end of the capacitor is grounded;
one section of the resistor is connected with the drain electrode of the amorphous ferroelectric field effect transistor, and the other end of the resistor is connected with the switch in series and then grounded.
In a possible implementation manner of the first aspect, the pulse signal generating device generates a pulse voltage for simulating excitatory stimulation of the input neuron.
A second aspect of an embodiment of the present application provides a control method of a neuron simulation device, which is applied to the neuron simulation device, and the control method includes:
when the neuron simulation device is in an initialized state, a first power supply is turned on to supply power to the second module, the pulse signal generating device is turned off, and the third module is disconnected from the first module;
opening the pulse signal generating device, and enabling the pulse signal generating device to generate pulse voltage and then charge the first module through the second module, so that the first module and the second module respectively simulate the accumulation characteristic and the leakage characteristic of the neuron;
detecting a voltage value of the first module, and when the voltage value of the first module reaches a preset threshold value, conducting connection between the third module and the first module so as to enable the third module to simulate the emission characteristic of the neuron in a first preset duration;
the control pulse signal generating device is in a closing state within a second preset time period so as to enable the neuron simulation device to be restored to an initialization state.
In a possible implementation manner of the second aspect, the first module and the second module simulate accumulation characteristics and leakage characteristics of neurons, specifically:
when the pulse signal generating device is turned on, the pulse signal generating device generates pulse voltage and then inputs the pulse voltage into the amorphous ferroelectric field effect transistor of the second module, so that the second module can simulate the leakage characteristic of the neuron;
when the pulse voltage charges the capacitor in the first module through the second module, the first module can simulate the accumulation characteristic of the neuron.
In a possible implementation manner of the second aspect, the third module simulates the emission characteristic of the neuron in the first preset duration, specifically:
when the voltage value of the first module reaches a preset threshold value, a switch in the third module is closed, and the connection between the third module and the first module is conducted; the capacitance of the first module is discharged through the resistor in the third module, so that the third module can simulate the emission characteristic of the neuron in the first preset time period.
In a possible implementation manner of the second aspect, the neuron simulation device is restored to an initialized state, specifically:
when the control pulse signal generating device is in a closed state within a second preset time period, the connection between the pulse signal generating device and the grid electrode of the amorphous ferroelectric field effect transistor is disconnected, and under the action of the polarization degradation characteristic of the amorphous ferroelectric field effect transistor, the amorphous ferroelectric field effect transistor is restored to an initial polarization state, so that the neuron simulation device can be restored to an initialization state.
Compared with the prior art, the neuron simulation device and the control method thereof provided by the embodiment of the invention have the beneficial effects that: the neuron simulation device provided by the embodiment of the invention comprises a first module, a second module and a third module, wherein the first module and the third module are connected with the second module, and the second module is also connected with a first power supply and a pulse signal generating device outside the neuron simulation device respectively. By the cooperation of the first module, the second module and the third module, accumulation, leakage and emission characteristics of neurons can be simulated; and the second module comprises an amorphous ferroelectric field effect transistor, and the neuron simulation device can be restored to an initialized state under the action of polarization degradation characteristics of the amorphous ferroelectric field effect transistor. The neuron simulation device improves the operation simplicity of neuron simulation and improves the simulation effect of neurons.
Drawings
FIG. 1 is a schematic diagram of a neuron simulation device according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a connection relationship of a neuron modeling apparatus according to an embodiment of the present invention;
fig. 3 is a flowchart of a control method of a neuron simulation device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a neuron simulation device according to an embodiment of the present invention, including: a first module 101, a second module 102, a third module 103.
As can be taken from fig. 1, the first module 101 and the third module 103 are connected to the second module 102, and the second module 102 is also connected to a first power source 104 and a pulse signal generating device 105, which are outside the neuron simulation device, respectively.
In this embodiment, the second module 102 includes an amorphous ferroelectric field effect transistor, and the second module 102 is configured to restore the neuron simulation device to an initialized state under the effect of polarization degradation characteristics of the amorphous ferroelectric field effect transistor; the first module 101, the second module 102 and the third module 103 are used to simulate the accumulation, leakage and emission characteristics of the neurons, respectively.
In one embodiment, the pulse signal generator 105 generates a pulse voltage for simulating excitatory stimulation of the input neurons.
For further explanation, referring to fig. 2, fig. 2 is a schematic diagram showing a specific connection relationship between the second module 102 and the first power source 104 and the pulse signal generating device 105, which are outside the first module 101, the third module 103, and the neuron simulation device.
As can be taken from fig. 2, the first module 101 and the third module 103 are both connected to the second module 102, and the second module 102 is further connected to a first power source 104 and a pulse signal generating device 105 outside the neuron analog device, specifically:
the second module 102 includes an amorphous ferroelectric field effect transistor 1021, and a drain d of the amorphous ferroelectric field effect transistor 1021 is connected to the first module 101 and the third module 103, respectively; the source s of the amorphous ferroelectric field effect transistor 1021 is connected to the first power source 104 outside the neuron analog device, and the gate g of the amorphous ferroelectric field effect transistor 1021 is connected to the pulse signal generating device 105 outside the neuron analog device.
Wherein the pulse signal generating means 105 generates a pulse voltage for simulating excitatory stimulation of the input neurons.
In a specific embodiment, the drain d of the amorphous ferroelectric field effect transistor 1021 is connected to the first module 101 and the third module 103 respectively, specifically:
the first module 101 comprises a capacitor C, and the third module 103 comprises a resistor R and a switch S1;
one end of the capacitor C is connected with the drain electrode d of the amorphous ferroelectric field effect transistor, and the other end of the capacitor C is grounded;
one section of the resistor R is connected with the drain electrode d of the amorphous ferroelectric field effect transistor, and the other end of the resistor R is connected with the switch S1 in series and then grounded.
In a specific embodiment, the Amorphous ferroelectric field effect transistor 1021 may be an amorphlus HfO2 FET device, an amorphlus ZrO2 FET device, or an amorphlus Al2O3 FET device, and the thickness of the Amorphous ferroelectric field effect transistor gate dielectric material is 2nm to 10nm, and the annealing temperature is 350 ℃ to 550 ℃; the gate of the Amorphos HfO2 FET device is used for receiving input excitatory stimulus, and the source is connected to VDD; the drain electrode is connected with one end of the capacitor and one end of the resistor respectively and is used as the output of the neuron. The other ends of the capacitor and the resistor are grounded.
To further explain the control method of the neuron simulation device, please refer to fig. 3, fig. 3 is a flow chart of a control method of the neuron simulation device according to an embodiment of the present invention, which includes:
s301: when the neuron simulation device is in an initialized state, a first power supply is turned on to supply power to the second module, the pulse signal generating device is turned off, and the third module is disconnected from the first module.
S302: the pulse signal generating device is turned on, and the pulse voltage is generated by the pulse signal generating device and then is charged to the first module through the second module, so that the first module and the second module respectively simulate the accumulation characteristic and the leakage characteristic of the neuron.
In this embodiment, after the pulse signal generating device is turned on, the pulse signal generating device generates a pulse voltage and inputs the pulse voltage into the amorphous ferroelectric field effect transistor of the second module, so that the second module can simulate the leakage characteristic of the neuron; the pulsed voltage, when used to charge the capacitor in the first module through the second module, enables the first module to simulate the accumulation characteristics of the neuron.
S303: and detecting the voltage value of the first module, and when the voltage value of the first module reaches a preset threshold value, conducting the connection between the third module and the first module so as to enable the third module to simulate the emission characteristic of the neuron in a first preset duration.
In this embodiment, when the voltage value of the first module reaches a preset threshold, the switch in the third module is closed, and the connection between the third module and the first module is turned on; the capacitance of the first module is discharged through the resistor in the third module, enabling the third module to simulate the firing characteristics of the neuron for a first predetermined period of time.
S304: the control pulse signal generating device is in a closing state within a second preset time period so as to enable the neuron simulation device to be restored to an initialization state.
In this embodiment, when the pulse signal generating device is controlled to be in the off state within the second preset period, because the connection between the pulse signal generating device and the gate of the amorphous ferroelectric field effect transistor is disconnected, under the effect of the polarization degradation characteristic of the amorphous ferroelectric field effect transistor, the amorphous ferroelectric field effect transistor is restored to the initial polarization state, and then the neuron simulation device is restored to the initialization state.
In this embodiment, since the amorphous ferroelectric field effect transistor has polarization degradation characteristics, the amorphous ferroelectric field effect transistor can automatically recover to an initial polarization state according to its polarization degradation characteristics without applying an additional reset voltage when no pulse voltage is input, and the neuron simulation device can recover to the initial state.
The neuron simulation device provided by the embodiment of the invention comprises a first module, a second module and a third module, wherein the first module and the third module are connected with the second module, and the second module is also connected with a first power supply and a pulse signal generating device outside the neuron simulation device respectively. By the cooperation of the first module, the second module and the third module, accumulation, leakage and emission characteristics of neurons can be simulated; and the second module comprises an amorphous ferroelectric field effect transistor, and the neuron simulation device can be restored to an initialized state under the action of polarization degradation characteristics of the amorphous ferroelectric field effect transistor. By the device, the neuron simulation device can automatically recover to an initialized state by utilizing the polarization degradation characteristic of the amorphous ferroelectric field effect transistor; without the need for the FeFET-containing neuron simulation device of the prior art: the neuron simulation device can be restored to an initialized state only by applying reset voltage, so that the operation simplicity of neuron simulation is improved, and the simulation effect of neurons is improved; meanwhile, compared with the prior art that a neuron simulation device is formed by using MOSFETs, the invention can form the neuron simulation device by only one amorphous ferroelectric field effect transistor, one switch, one resistor and one capacitor, thereby greatly reducing the hardware cost of the neuron simulation device.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (5)
1. A neuron simulation apparatus, comprising: a first module, a second module, and a third module for simulating an accumulation characteristic, a leakage characteristic, and a transmission characteristic of the neuron, respectively;
wherein the second module comprises an amorphous ferroelectric field effect transistor having polarization degradation characteristics for restoring the neuron analog device to an initialized state;
the first module and the third module are connected with the second module, and the second module is also connected with a first power supply and a pulse signal generating device outside the neuron simulation device respectively;
when the neuron simulation device is in an initialized state, the first power supply is turned on to supply power to the second module, the pulse signal generation device is turned off, and the third module is disconnected from the first module;
opening the pulse signal generating device, and enabling the pulse signal generating device to generate pulse voltage and then charging the first module through the second module, so that the first module and the second module respectively simulate the accumulation characteristic and the leakage characteristic of the neuron;
detecting the voltage value of the first module, and when the voltage value of the first module reaches a preset threshold value, conducting the connection between the third module and the first module so that the third module simulates the emission characteristic of the neuron in a first preset duration;
controlling the pulse signal generating device to be in a closed state within a second preset time period so as to enable the neuron simulation device to be restored to the initialization state;
the first module and the second module respectively simulate the accumulation characteristic and the leakage characteristic of the neuron, and specifically comprise the following steps:
when the pulse signal generating device is turned on, the pulse signal generating device generates pulse voltage and inputs the pulse voltage into the amorphous ferroelectric field effect transistor of the second module, so that the second module can simulate the leakage characteristic of the neuron;
when the pulse voltage charges the capacitor in the first module through the second module, the first module can simulate the accumulation characteristic of the neuron;
the third module simulates the emission characteristics of neurons in a first preset time period, and specifically comprises the following steps:
when the voltage value of the first module reaches a preset threshold value, the switch in the third module is closed, and the connection between the third module and the first module is conducted; the capacitance of the first module is discharged through the resistor in the third module, enabling the third module to simulate the firing characteristics of the neuron for a first predetermined period of time.
2. The neuron simulation device according to claim 1, wherein the first module and the third module are connected to the second module, and the second module is further connected to a first power supply and a pulse signal generating device outside the neuron simulation device, specifically:
the drain electrode of the amorphous ferroelectric field effect transistor is respectively connected with the first module and the third module; the source electrode of the amorphous ferroelectric field effect transistor is connected with the first power supply outside the neuron simulation device, and the grid electrode of the amorphous ferroelectric field effect transistor is connected with the pulse signal generating device outside the neuron simulation device.
3. The neuron simulation device according to claim 2, wherein the drains of the amorphous ferroelectric field effect transistors are connected to the first and third modules, respectively, in particular:
the first module comprises a capacitor, and the third module comprises a resistor and a switch;
one end of the capacitor is connected with the drain electrode of the amorphous ferroelectric field effect transistor, and the other end of the capacitor is grounded;
one section of the resistor is connected with the drain electrode of the amorphous ferroelectric field effect transistor, and the other end of the resistor is connected with a switch in series and then grounded.
4. A neuron simulation apparatus according to claim 3, wherein said pulse signal generating means generates pulse voltages for simulating excitatory stimuli to be input to said neurons.
5. A control method of a neuron simulation device, applied to the neuron simulation device according to claim 1, wherein the neuron simulation device returns to the initialized state, specifically:
and when the pulse signal generating device is controlled to be in a closed state within a second preset time period, the connection between the pulse signal generating device and the grid electrode of the amorphous ferroelectric field effect transistor is disconnected, and under the action of the polarization degradation characteristic of the amorphous ferroelectric field effect transistor, the amorphous ferroelectric field effect transistor is restored to an initial polarization state, so that the neuron simulation device can be restored to the initial state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110377708.9A CN113177637B (en) | 2021-04-08 | 2021-04-08 | Neuron simulation device and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110377708.9A CN113177637B (en) | 2021-04-08 | 2021-04-08 | Neuron simulation device and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113177637A CN113177637A (en) | 2021-07-27 |
| CN113177637B true CN113177637B (en) | 2024-01-30 |
Family
ID=76924583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110377708.9A Active CN113177637B (en) | 2021-04-08 | 2021-04-08 | Neuron simulation device and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113177637B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446762A (en) * | 2018-03-30 | 2018-08-24 | 广西师范大学 | A kind of hardware circuit of the analog pulse neuron based on MOS field-effect transistors and its application |
| CN110232440A (en) * | 2019-06-11 | 2019-09-13 | 北京大学 | Spiking neuron circuit based on ferroelectric transistor |
| CN110309908A (en) * | 2019-06-11 | 2019-10-08 | 北京大学 | FeFET-CMOS mixed pulses neuron based on ferroelectric transistor |
| WO2019192462A1 (en) * | 2018-04-02 | 2019-10-10 | 北京大学 | Multi-mode neuron circuit and neuron implementation method |
| CN112434802A (en) * | 2020-11-06 | 2021-03-02 | 北京大学 | Method for realizing self-adaptive random pulse neuron based on ferroelectric transistor |
-
2021
- 2021-04-08 CN CN202110377708.9A patent/CN113177637B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446762A (en) * | 2018-03-30 | 2018-08-24 | 广西师范大学 | A kind of hardware circuit of the analog pulse neuron based on MOS field-effect transistors and its application |
| WO2019192462A1 (en) * | 2018-04-02 | 2019-10-10 | 北京大学 | Multi-mode neuron circuit and neuron implementation method |
| CN110232440A (en) * | 2019-06-11 | 2019-09-13 | 北京大学 | Spiking neuron circuit based on ferroelectric transistor |
| CN110309908A (en) * | 2019-06-11 | 2019-10-08 | 北京大学 | FeFET-CMOS mixed pulses neuron based on ferroelectric transistor |
| CN112434802A (en) * | 2020-11-06 | 2021-03-02 | 北京大学 | Method for realizing self-adaptive random pulse neuron based on ferroelectric transistor |
Non-Patent Citations (1)
| Title |
|---|
| 蔺想红 ; 张田文 ; .指数突触电导IF神经元模型及事件驱动模拟策略.电子学报.2008,(第08期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113177637A (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6906602B2 (en) | Artificial neuron | |
| CN108880529B (en) | Pulse neuron circuit based on tunneling field effect transistor | |
| CN110232440B (en) | Pulse neuron circuit based on ferroelectric transistor | |
| CN110309908B (en) | FeFET-CMOS mixed pulse neuron circuit based on ferroelectric transistor | |
| CN109816096B (en) | Memristor-based perceptron neural network circuit and adjusting method thereof | |
| CN112465134B (en) | Pulse neural network neuron circuit based on LIF model | |
| CN111291877B (en) | Ferroelectric transistor FeFET-based side-inhibitory neuron circuit | |
| CN113177637B (en) | Neuron simulation device and control method thereof | |
| Khanday et al. | Single SiGe transistor based energy-efficient leaky integrate-and-fire neuron for neuromorphic computing | |
| CN114528984A (en) | Multi-input neuron circuit for impulse neural network | |
| Shi et al. | A summating, exponentially-decaying CMOS synapse for spiking neural systems | |
| CN109102072B (en) | Memristor synaptic pulse neural network circuit design method based on single-electron transistor | |
| Khanday et al. | An energy‐efficient tunable threshold spiking neuron with excitatory and inhibitory function | |
| Zhu et al. | Leaky Integrate‐and‐Fire Neuron Based on Organic Electrochemical Transistor for Spiking Neural Networks with Temporal‐Coding | |
| Sowparna et al. | A proposal of energy efficient ferroelectric PDSOI LIF neuron for spiking neural network applications | |
| Shah et al. | FinFET based photoreceptor for silicon retina to reduce power consumption | |
| US11868868B2 (en) | Method for implementing adaptive stochastic spiking neuron based on ferroelectric field effect transistor | |
| Kwon et al. | Integrate-and-fire neuron circuit and synaptic device using floating body MOSFET with spike timing-dependent plasticity | |
| US11551070B2 (en) | Artificial neuromorphic circuit and operation method | |
| Afrin et al. | R (t)-Based Spike-Timing-Dependent Plasticity in Memristive Neural Networks | |
| KR102062666B1 (en) | Input modulating adaptive neuron circuit | |
| Shibata et al. | A self-learning neural-network LSI using neuron MOSFETs | |
| CN113962373B (en) | Method for realizing nerve morphology device with synaptic and neuron functions | |
| CN110766149A (en) | Discharge rate dependent plasticity structure and implementation method | |
| CN109242095B (en) | Charge injection type neuron network array |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |