Limits...
A novel memristive multilayer feedforward small-world neural network with its applications in PID control.

Dong Z, Duan S, Hu X, Wang L, Li H - ScientificWorldJournal (2014)

Bottom Line: More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons.Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy.Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

View Article: PubMed Central - PubMed

Affiliation: School of Electronics and Information Engineering, Southwest University, Chongqing 400715, China.

ABSTRACT
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

Show MeSH
The principle diagram of the memristive activation function in the hidden layer. (a) The Simulink model of the memristive activation function in the hidden layer. (b) The curve of the memristive activation function h(x).
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4150482&req=5

fig9: The principle diagram of the memristive activation function in the hidden layer. (a) The Simulink model of the memristive activation function in the hidden layer. (b) The curve of the memristive activation function h(x).

Mentions: Figure 9(a) exhibits the constructing principle diagram of the memristive activation function in the hidden layer, in which the red dotted line frame represents the parameter adjustment area. K1 is the adjustable gain which is used for controlling the shape of the activation function, and K2 is the fixed gain whose value is K2 = 10−4. The suitable parameters of the memristor are chosen as Ron⁡ = 100 Ω, Roff⁡ = 20 kΩ, M0 = 10 kΩ, D = 10 nm, and μν ≈ 10−14m2s−1V−1. The input signal is a sinusoidal current with an amplitude of 0.5 mA and a frequency of 1 Hz. Notably, the polarity of the voltage applied into the memristor is opposite to the polarity of the memristor itself; that is, the current flows through the memristor from the negative polar to the positive polar. Figure 9(b) shows the memristive activation function of the hidden layer, and its shape varies with different values of K1.


A novel memristive multilayer feedforward small-world neural network with its applications in PID control.

Dong Z, Duan S, Hu X, Wang L, Li H - ScientificWorldJournal (2014)

The principle diagram of the memristive activation function in the hidden layer. (a) The Simulink model of the memristive activation function in the hidden layer. (b) The curve of the memristive activation function h(x).
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4150482&req=5

fig9: The principle diagram of the memristive activation function in the hidden layer. (a) The Simulink model of the memristive activation function in the hidden layer. (b) The curve of the memristive activation function h(x).
Mentions: Figure 9(a) exhibits the constructing principle diagram of the memristive activation function in the hidden layer, in which the red dotted line frame represents the parameter adjustment area. K1 is the adjustable gain which is used for controlling the shape of the activation function, and K2 is the fixed gain whose value is K2 = 10−4. The suitable parameters of the memristor are chosen as Ron⁡ = 100 Ω, Roff⁡ = 20 kΩ, M0 = 10 kΩ, D = 10 nm, and μν ≈ 10−14m2s−1V−1. The input signal is a sinusoidal current with an amplitude of 0.5 mA and a frequency of 1 Hz. Notably, the polarity of the voltage applied into the memristor is opposite to the polarity of the memristor itself; that is, the current flows through the memristor from the negative polar to the positive polar. Figure 9(b) shows the memristive activation function of the hidden layer, and its shape varies with different values of K1.

Bottom Line: More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons.Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy.Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

View Article: PubMed Central - PubMed

Affiliation: School of Electronics and Information Engineering, Southwest University, Chongqing 400715, China.

ABSTRACT
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

Show MeSH