Gain-adjustable neuron circuit and control method thereof

Abstract

The invention relates to a gain-adjustable neuron circuit and a control method thereof, the gain-adjustable neuron circuit comprises a memristive element, a capacitor and a resistor, one end of the memristive element is connected with the capacitor in parallel, then is connected with the resistor in series, and is connected with a driving power supply; the memristive element comprises an MIM structure, a heating module for providing a thermal field for the MIM structure and a substrate for providing support for the whole memristive element, the MIM structure comprises a top electrode, a functional layer and a bottom electrode which are sequentially distributed from top to bottom, the heating module comprises a heat conduction layer and a heating layer which are sequentially distributed, and the heating layer is in contact with the MIM structure through the heat conduction layer for heat transfer; the top electrode is connected with driving type voltage input, and the bottom electrode is grounded; one end of the heating layer is connected with modulation type voltage input, and the other end is grounded; and a port, connected with the resistor, of the memristor element is a voltage output end. Compared with the prior art, the pulse response to driving type input can be realized, and the dynamic adjustment of the response gain is also realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of neuron circuit, and particularly to a gain-adjustable neuron circuit and a control method thereof. BACKGROUND

[0002] Spiking neural network (SNN) is considered as the first choice for building high energy-efficient data processing unit with integrated computing, and its core includes neurons and synapses, especially spiking neuron circuits with rich dynamic characteristics. This kind of circuit simulates the process of generating electrical pulses (i.e. action potential) when biological neurons receive external stimuli, and realizes the similar pulse response characteristics of biological neurons.

[0003] Traditional CMOS technology faces many challenges in implementing spiking neuron circuits, often requiring the help of complex auxiliary circuits to simulate biological dynamics. The energy consumption and integration density are far from biological units. With the end of Moore's law, using new principle devices such as memristors to realize neuron circuits is a new field. New neuromorphic devices become the ideal choice for building neuron circuits due to their small area, compactness, low energy consumption and rich dynamics.

[0004] However, although the existing neuron circuits based on new devices can realize the basic threshold response characteristics of neurons, they still cannot effectively realize the gain-adjustable characteristics of biological neurons. Gain refers to the response sensitivity of neurons to input (corresponding to the slope of the neuron input-output curve). Gain modulation refers to the ability of neurons to accept additional input to adjust the response sensitivity to current synaptic input, which is crucial for simulating the adaptability and flexibility of biological neurons in different physiological states. At present, most neuron circuits based on new devices only simulate the basic characteristics of neuron firing pulses, and cannot provide dynamically adjustable gain response. Therefore, future research needs to further optimize device characteristics and circuit design to realize more rich and complex biological characteristics of neuron circuits. SUMMARY

[0005] The purpose of the present application is to overcome the defects of the prior art and provide a gain-adjustable neuron circuit and a control method thereof, which can not only realize the pulse response to the driving input, but also realize the dynamic adjustment of the response gain.

[0006] The purpose of the present application can be achieved by the following technical solutions: A gain-adjustable neuron circuit includes a memristor element, a capacitor and a resistor, one end of the memristor element is connected in parallel with the capacitor, and then connected in series with the resistor, and a driving power supply is connected. The memory resistance element comprises a MIM structure, a heating module providing a thermal field for the MIM structure, and a substrate providing support for the whole memory resistance element, the MIM structure comprises a top electrode, a functional layer and a bottom electrode arranged in sequence from top to bottom, the heating module comprises a heat-conducting layer and a heating layer arranged in sequence, and the heating layer is in contact with the MIM structure through the heat-conducting layer for heat transfer; The top electrode is connected with a driving type voltage input, and the bottom electrode is grounded; one end of the heating layer is connected with a modulation type voltage input, and the other end is grounded; and the port connected with the resistance of the memory resistance element is a voltage output end.

[0007] Further, the resistance, the memory resistance element and the capacitor constitute a charging circuit, and the memory resistance element and the capacitor constitute a discharging circuit.

[0008] Further, when the driving power supply works, one end of the functional layer receives the driving type voltage input and charges the capacitor; when the voltage division of the functional layer at two ends exceeds the threshold voltage of the functional layer material, the functional layer jumps from a high resistance state to a low resistance state, and the capacitor is discharged through the memory resistance element until the voltage division of the functional layer is lower than the holding voltage of the functional layer material, and the functional layer returns to the high state, so as to complete one pulse emission of the neuron circuit.

[0009] Further, when the modulation type voltage input is applied to the heating layer, the heating layer generates a thermal field and conducts the thermal field to the functional layer through the heat-conducting layer, so as to change the threshold voltage and the holding voltage of the functional layer and adjust the pulse response sensitivity of the neuron circuit.

[0010] Further, the substrate is a silicon oxide substrate.

[0011] The application further provides a control method of the gain-adjustable neuron circuit. The neuron circuit is input with a voltage by a driving power supply, a driving type voltage input is applied to the top electrode and the capacitor is charged, so that the voltage at two ends of the functional layer increases, when the voltage division at two ends of the functional layer exceeds the threshold voltage, the material of the functional layer jumps from a high resistance state to a low resistance state and is discharged from the capacitor, until the voltage division of the functional layer is lower than the holding voltage of the material, the material of the functional layer returns to the high resistance state, and one pulse emission of the neuron circuit is completed; After a modulation type voltage input is applied to the heating layer, a thermal field generated by the heating layer is conducted to the functional layer, so as to change the threshold voltage and the holding voltage of the material of the functional layer and change the pulse emission frequency of the neuron circuit.

[0012] The application further provides another gain-adjustable neuron circuit, comprising a memory resistance element, a capacitor and a resistance, one end of the memory resistance element is connected in parallel with the capacitor and in series with the resistance. The memristor element comprises a MIM structure, and the MIM structure comprises a top electrode, a functional layer and a bottom electrode arranged in sequence from top to bottom. One end of the resistor is connected with a driving power supply, the other end is connected with the top electrode and serves as a voltage output end, and the top electrode receives voltage input after voltage division by the resistor; and the bottom electrode receives modulated voltage input.

[0013] Further, by applying modulated voltage input to the bottom electrode, voltage input of the top electrode is correspondingly adjusted, so that threshold switch behavior of the neuron circuit is linearly adjusted along the input direction.

[0014] Further, when the driving power supply works, one end of the functional layer receives voltage input after voltage division by the top electrode, and the other end receives modulated voltage input of the bottom electrode, and when a potential difference between both ends of the functional layer exceeds a threshold voltage of the functional layer material, the functional layer jumps from a high resistance state to a low resistance state, and is discharged by the capacitor through the memristor element until the voltage division of the functional layer is lower than a holding voltage of the functional layer material, and the functional layer returns to the high state, so that one pulse emission of the neuron circuit is completed.

[0015] The application further provides a control method of the gain-adjustable neuron circuit, and the control method comprises the following steps: The neuron circuit is input with voltage by the driving power supply, and the voltage is applied to the top electrode after voltage division by the resistor, and modulated voltage input is applied to the bottom electrode and conducted to both ends of the functional layer; when a potential difference between both ends of the functional layer exceeds a threshold voltage of the functional layer material, the functional layer jumps from a high resistance state to a low resistance state, and is discharged by the capacitor through the memristor element until the voltage division of the functional layer is lower than a holding voltage of the functional layer material, and the functional layer returns to the high state, so that one pulse emission of the neuron circuit is completed. By adjusting the size of the modulated voltage input applied to the bottom electrode, threshold switch behavior of the neuron circuit is linearly adjusted along the input direction.

[0016] Compared with the prior art, the application has the following advantages: (1) The gain-adjustable neuron circuit provided by the application generates a large current by setting a heating layer and receiving modulated input, and then generates a heat field and conducts the heat field to the functional layer of the memristor element through a heat conduction layer; the threshold voltage and the holding voltage of the functional layer material change under the action of the heat field, and thus the charging and discharging process of the neuron circuit changes, and then the pulse emission frequency of the circuit changes. The change of the pulse response sensitivity of the neuron to the driving input caused by the modulated input realizes the gain modulation characteristic of the biological neuron.

[0017] (2) The other gain-adjustable neuron circuit provided by the application adjusts the input of the modulation type voltage to the bottom electrode, and the potential difference between the two ends of the functional layer determines the threshold response behavior of the device. If the voltage input of the top electrode of the device is increased to ensure that the voltage of the functional layer is still higher than the threshold voltage of the material, the threshold switching behavior of the neuron only has a linear translation along the input direction. Therefore, the input of the modulation type received by the bottom electrode also changes the pulse firing behavior of the neuron circuit to the same driving voltage, which is a linear integration of the input of the modulation type and the input of the driving type, and is also considered to be a kind of gain modulation characteristic of the biological neuron. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A structure schematic diagram of a gain-adjustable neuron circuit provided in embodiment 1 of the application; Figure 2 A structure schematic diagram of a memristor element of the gain-adjustable neuron circuit provided in embodiment 1 of the application; Figure 3 A voltage input schematic diagram of the gain-adjustable neuron circuit provided in embodiment 1 of the application; Figure 4 A voltage oscillation waveform diagram of the gain-adjustable neuron circuit provided in embodiment 1 of the application under different modulation type inputs V m Figure 5 A diagram of the change of the pulse response frequency of the gain-adjustable neuron circuit provided in embodiment 1 of the application under the driving type input V d Figure 6 A structure schematic diagram of a gain-adjustable neuron circuit provided in embodiment 2 of the application; Figure 7 A voltage input schematic diagram of the gain-adjustable neuron circuit provided in embodiment 2 of the application; Figure 8 An integration effect diagram of the gain-adjustable neuron circuit provided in embodiment 2 of the application under the constant voltage input; Figure 9 A voltage oscillation waveform diagram of the gain-adjustable neuron circuit provided in embodiment 2 of the application under different modulation type inputs V b Figure 10 A diagram of the change of the pulse response frequency of the gain-adjustable neuron circuit provided in embodiment 2 of the application under the driving type input. DETAILED DESCRIPTION

[0019] ​​​In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0021] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0022] Embodiment 1 As shown in Figure 1 and Figure 2 The embodiment provides a gain-adjustable neuron circuit, which comprises a memristor, a capacitor and a resistor, one end of the memristor is connected in parallel with the capacitor, then connected in series with the resistor, and a driving power supply is connected. The memristor comprises an MIM structure, a heating module for providing a thermal field for the MIM structure, and a substrate for providing support for the whole memristor, the MIM structure comprises a top electrode I6, a functional layer I5 and a bottom electrode I4 distributed in sequence from top to bottom, the heating module comprises a heat-conducting layer I3 and a heating layer I2 distributed in sequence, and the heating layer I2 is in contact with the MIM structure through the heat-conducting layer I3 to transfer heat. The top electrode I6 is connected with a driving type voltage input, and the bottom electrode I4 is grounded; one end of the heating layer I2 is connected with a modulating type voltage input, and the other end is grounded; and the port where the memristor is connected with the resistor is a voltage output end.

[0023] The resistor, the memristor and the capacitor constitute a charging loop, and the memristor and the capacitor constitute a discharging loop.

[0024] The substrate can be a silicon oxide substrate I1.

[0025] Working principle: as shown in Figure 3As shown, when the driving power source works, one end of the functional layer receives the driving-type voltage input and charges the capacitor; when the voltage across the two ends of the functional layer exceeds the threshold voltage of the functional layer material, the functional layer jumps from the high resistance state to the low resistance state, and the capacitor discharges through the memristive element until the voltage across the functional layer is lower than the holding voltage of the functional layer material, the functional layer returns to the high state, thereby completing a pulse firing of the neuron circuit.

[0026] When the modulated-type voltage input is applied to the heating layer, the heating layer generates a thermal field and conducts the thermal field to the functional layer through the thermal conductive layer, so as to change the threshold voltage and the holding voltage of the functional layer material, thereby adjusting the pulse response sensitivity of the neuron circuit.

[0027] The embodiment also provides a control method of the gain-adjustable neuron circuit. The neuron circuit is input with a voltage by the driving power source, the driving-type voltage input is applied to the top electrode, and the capacitor is charged, so that the voltage across the two ends of the functional layer increases; when the voltage across the two ends of the functional layer exceeds the threshold voltage, the material of the functional layer jumps from the high resistance state to the low resistance state, and the capacitor discharges until the voltage across the functional layer is lower than the holding voltage of the material, the material of the functional layer returns to the high resistance state, and a pulse firing of the neuron circuit is completed; When the modulated-type voltage input is applied to the heating layer, the thermal field generated by the heating layer conducts to the functional layer, so as to change the threshold voltage and the holding voltage of the functional layer material, and further change the pulse firing frequency of the neuron circuit.

[0028] Specifically, in the embodiment, the neuron circuit is formed by connecting a threshold-adjustable memristive element and an external capacitor in parallel and connecting the parallel connection with a resistor in series. The top electrode of the memristive element serves as an input end and receives a driving-type input V d The port connected with the resistor R C serves as a voltage output end, and the bottom electrode of the memristive element is grounded. The other port of the resistor is connected with a driving power source V DD . One end of the heating layer of the memristive element serves as a voltage input end and receives a modulated-type input V m , and the other end is grounded. The resistor, the memristive element and the capacitor form a charging circuit, and the memristive element and the capacitor form a discharging circuit.

[0029] The top electrode, the functional layer, the bottom electrode, the thermal conductive layer, the heating layer and the silicon oxide substrate are sequentially distributed from top to bottom.

[0030] In the neuron circuit, when the driving power source V DD works, due to the series voltage division, one end of the functional layer of the memristive element receives the driving-type input V d and charges the capacitor, and the voltage across the two ends of the functional layer increases. When the voltage across the two ends of the functional layer exceeds the threshold voltage V thWhen the material transitions from a high-resistivity state to a low-resistivity state, the voltage drop across the functional layer decreases, and the capacitor discharges through the memristor until the voltage drop across the functional layer falls below the material's holding voltage V. hold At this point, the material abruptly returns to a high-resistivity state, thus completing one pulse firing of the neuron circuit. When a modulated voltage V is applied to the heating layer of the memristor element... m Subsequently, the heating layer generates a large current, which in turn creates a thermal field that is conducted to the functional layer of the memristor element through the thermally conductive layer. The threshold voltage V of the material... th and holding voltage V hold The change in the thermal field alters the charging and discharging processes of the neuron circuit, leading to a change in the pulse firing frequency. This alteration of the neuron's pulse response sensitivity to the driving input, caused by the modulated input, achieves the gain modulation characteristic of biological neurons.

[0031] like Figure 1 As shown, this is a neuron circuit receiving modulated input V in the memristor element heating layer. m The diagram below illustrates this.

[0032] like Figure 4 As shown, this illustrates the neuron circuit under different modulation input V. m The voltage oscillation waveform under the given conditions. When V m As the heating layer of the device increases, the thermal field generated increases, the threshold voltage of the neuron decreases, and the oscillation window also decreases accordingly.

[0033] like Figure 5 As shown, this is a neuron circuit with a driving input V. d The graph shows the change in pulse response frequency as a function of the modulated input. When V m As the memristor's heating layer increases, the thermal field generated increases, the threshold voltage decreases, the integration process under the same drive input speeds up, and the pulse firing frequency increases. This can be seen in the figure as V m The modulation behavior of the response to the driving input is similar to the multiplication and division gain modulation characteristics in biology.

[0034] Example 2 like Figure 6 As shown, this embodiment provides a gain-adjustable neuron circuit, including a memristor element, a capacitor, and a resistor. One end of the memristor element is connected in parallel with the capacitor and then in series with the resistor. Memristor devices include a MIM structure, which includes a top electrode, a functional layer, and a bottom electrode arranged sequentially from top to bottom. One end of the resistor is connected to the driving power supply, and the other end is connected to the top electrode and serves as the voltage output terminal. The top electrode receives the voltage input after being divided by the resistor; the bottom electrode receives a modulated voltage input.

[0035] Working principle: by applying a modulated voltage input to the bottom electrode, the voltage input to the top electrode is adjusted accordingly, to achieve linear translation adjustment of the threshold switch behavior of the neuron circuit along the input direction.

[0036] When the driving power source is working, one end of the functional layer receives the voltage input after resistance voltage division of the top electrode, and the other end receives the modulated voltage input of the bottom electrode. When the potential difference between the two ends of the functional layer exceeds the threshold voltage of the functional layer material, the functional layer jumps from a high resistance state to a low resistance state, and discharges through the memristor element until the functional layer restores to the high state when the functional layer voltage is lower than the holding voltage of the functional layer material, thus completing a pulse firing of the neuron circuit.

[0037] The embodiment also provides a control method of the gain-adjustable neuron circuit, comprising the following steps: The neuron circuit is input with voltage by the driving power source, and the voltage is applied to the top electrode after resistance voltage division. The modulated voltage input is applied to the bottom electrode and conducted to both ends of the functional layer. When the potential difference between the two ends of the functional layer exceeds the threshold voltage of the functional layer material, the functional layer jumps from a high resistance state to a low resistance state, and discharges through the memristor element until the functional layer restores to the high state when the functional layer voltage is lower than the holding voltage of the functional layer material, thus completing a pulse firing of the neuron circuit. The size of the modulated voltage input applied to the bottom electrode is adjusted to linearly translate the threshold switch behavior of the neuron circuit along the input direction.

[0038] Specifically, in the embodiment, the neuron circuit is composed of a threshold-adjustable memristor element and an external capacitor in parallel, and a resistor in series. The resistor R C has one port connected to the driving power source V DD . The other port of the resistor is connected to the top electrode of the memristor element and serves as a voltage output end. The top electrode of the memristor element receives the voltage input after resistance voltage division, and the bottom electrode receives the modulated voltage input, i.e., the bottom electrode potential is set to V bias , as shown in FIG. Figure 7 .

[0039] In the neuron circuit, the potential difference between the two ends of the functional layer of the memristor element determines the threshold response behavior of the device. A positive voltage bias V bias is applied to the bottom electrode of the memristor. To ensure that the functional layer voltage still exceeds the threshold voltage V th of the material, the voltage input to the top electrode of the device must be increased accordingly. In addition, since the functional layer is not subjected to a thermal field, the switching voltage window of the functional layer material has not changed.

[0040] In summary, the threshold switching behavior of neuron only happens a linear shift along the input direction. Therefore, the modulated input accepted by the bottom electrode also changes the neuron circuit's pulse firing behavior to the same driving voltage, which is a linear integration of modulated input and driving input, and is also considered as a gain modulation characteristic of biological neuron.

[0041] As shown in Figure 8 , the voltage charges the capacitor until the voltage exceeds the threshold voltage V th of the memristor, the neuron fires a pulse, and the capacitor discharges until the voltage is lower than the holding voltage V hold of the memristor, and the next integration starts. The repeatable integration firing behavior can be seen in Figure 8 . One integration firing is regarded as one pulse.

[0042] Figure 6 is a schematic diagram of the neuron circuit when the bottom electrode of the memristor element accepts a modulated input.

[0043] Figure 9 is a voltage oscillation waveform diagram of the neuron circuit under different modulated inputs V b . When V b increases, the source bias of the device increases, and in order to ensure the same voltage oscillation window, the drain voltage of the device increases, which is manifested as a linear upward shift of the voltage oscillation waveform of the neuron.

[0044] Figure 10 is a diagram of the change of the pulse response frequency of the neuron circuit under driving input with the change of modulated input. When the modulated voltage increases, the driving voltage required for the memristor to reach the threshold value increases. The integration process under the same driving input slows down, and the pulse firing frequency decreases. But this frequency reduction can be compensated by increasing the driving voltage of the same size as the modulated input, and in the figure, it can be seen that the input-output curve shifts to the right with the increase of the modulated voltage. This modulation behavior is similar to the gain modulation characteristics of biology.

[0045] The above describes the preferred embodiments of the present application in detail. It should be understood that those skilled in the art can make many modifications and changes without creative labor according to the concept of the present application. Therefore, any technical solution that can be obtained by logical analysis, reasoning or limited experiment by those skilled in the art on the basis of the prior art according to the concept of the present application shall be within the protection scope determined by the claims.

Claims

1. A neuron circuit with adjustable gain, characterized in that, The memory resistor element, the capacitor and the resistance are connected in series, and a driving power source is connected to the memory resistor element and the capacitor in parallel. The memory resistor element comprises a MIM structure, a heating module for providing a thermal field for the MIM structure, and a substrate for providing support for the whole memory resistor element. The top electrode is connected with a driving voltage input, and the bottom electrode is grounded.

2. A gain adjustable neuron circuit according to claim 1, wherein The memory resistor element and the capacitor constitute a charging circuit, and the memory resistor element and the capacitor constitute a discharging circuit.

3. The gain-adjustable neuron circuit according to claim 1, wherein When the driving power source works, one end of the functional layer receives the driving voltage input and charges the capacitor.

4. A gain adjustable neuron circuit according to claim 3, wherein When the voltage across the functional layer exceeds the threshold voltage of the functional layer material, the functional layer jumps from a high resistance state to a low resistance state, and the capacitor discharges through the memory resistor element until the voltage across the functional layer is lower than the holding voltage of the functional layer material, and the functional layer returns to the high resistance state, thereby completing a pulse emission of the neuron circuit.

5. The gain-adjustable neuron circuit according to claim 1, wherein When a modulated voltage input is applied to the heating layer, the heating layer generates a thermal field and conducts the thermal field to the functional layer through the heat-conducting layer, thereby changing the threshold voltage and the holding voltage of the functional layer and adjusting the pulse response sensitivity of the neuron circuit.

6. A method of controlling a gain-adjustable neuron circuit as claimed in any one of claims 1-5, characterized in that The substrate is a silicon oxide substrate. The method comprises the following steps: A voltage is input to the neuron circuit by a driving power source, a driving voltage input is applied to the top electrode, and the capacitor is charged, so that the voltage across the functional layer increases.

7. A gain adjustable neuron circuit, characterized by, When the voltage across the functional layer exceeds the threshold voltage, the material of the functional layer jumps from a high resistance state to a low resistance state, and the capacitor discharges until the voltage across the functional layer is lower than the holding voltage of the material, and the material of the functional layer returns to the high resistance state, thereby completing a pulse emission of the neuron circuit. When a modulated voltage input is applied to the heating layer, the thermal field generated by the heating layer is conducted to the functional layer, thereby changing the threshold voltage and the holding voltage of the functional layer and changing the pulse emission frequency of the neuron circuit. The memory resistor element, the capacitor and the resistance are connected in series.

8. A gain adjustable neuron circuit according to claim 7, wherein The memory resistor element comprises a MIM structure, and the MIM structure comprises a top electrode, a functional layer and a bottom electrode distributed in sequence from top to bottom. One end of the resistance is connected with a driving power source, and the other end is connected with the top electrode and serves as a voltage output end. By applying a modulated voltage input to the bottom electrode, the voltage input to the top electrode is adjusted, thereby realizing linear translation adjustment of the threshold switch behavior of the neuron circuit in the input direction.

9. A gain adjustable neuron circuit according to claim 7, wherein When the driving power source works, one end of the functional layer receives voltage input through resistance voltage division of the top electrode, and the other end receives modulated voltage input of the bottom electrode. When the potential difference between the two ends of the functional layer exceeds the threshold voltage of the functional layer material, the functional layer jumps from the high resistance state to the low resistance state, and discharges through the memristor element until the voltage of the functional layer is lower than the holding voltage of the functional layer material, and the functional layer returns to the high state, thereby completing a pulse emission of the neuron circuit.

10. A method of controlling a gain-adjustable neuron circuit as claimed in any one of claims 7-9, characterized in that The method comprises the following steps: A voltage is input to the neuron circuit by the driving power source, and is applied to the top electrode after resistance voltage division. A modulated voltage is input to the bottom electrode and is conducted to both ends of the functional layer. When the potential difference between the two ends of the functional layer exceeds the threshold voltage of the functional layer material, the functional layer jumps from the high resistance state to the low resistance state, and discharges through the memristor element until the voltage of the functional layer is lower than the holding voltage of the functional layer material, and the functional layer returns to the high state, thereby completing a pulse emission of the neuron circuit; The linear translation adjustment of the threshold switch behavior of the neuron circuit in the input direction is realized by adjusting the size of the modulated voltage input applied to the bottom electrode.

Images